allenai / robustnav Goto Github PK

View Code? Open in Web Editor NEW

27.0 6.0 3.0 16 MB

Evaluating pre-trained navigation agents under corruptions

Home Page: https://prior.allenai.org/projects/robustnav

License: Other

Python 99.06% Shell 0.90% HTML 0.04%

embodied-ai ai2thor-environment visual-navigation embodied-vision computer-vision deep-reinforcement-learning

robustnav's Introduction

RobustNav: Towards Benchmarking Robustness in Embodied Navigation

Prithvijit Chattopadhyay, Judy Hoffman, Roozbeh Mottaghi, Ani Kembhavi

(Project Page)

As an attempt towards assessing the robustness of embodied navigation agents, we propose RobustNav, a framework to quantify the performance of embodied navigation agents when exposed to a wide variety of visual – affecting RGB inputs – and dynamics – affecting transition dynamics – corruptions. Most recent efforts in visual navigation have typically focused on generalizing to novel target environments with similar appearance and dynamics characteristics. With RobustNav, we find that some standard embodied navigation agents significantly underperform (or fail) in the presence of visual or dynamics corruptions. We systematically analyze the kind of idiosyncrasies that emerge in the behavior of such agents when operating under corruptions. Finally, for visual corruptions in RobustNav, we show that while standard techniques to improve robustness such as data-augmentation and self-supervised adaptation offer some zero-shot resistance and improvements in navigation performance, there is still a long way to go in terms of recovering lost performance relative to clean “non-corrupt” settings, warranting more research in this direction.

RobustNav is based on AllenAct framework and the majority of the core training algorithms and pipelines are borrowed from a specific commit of the AllenAct code base.

Citation

If you find this project useful in your research, please consider citing:

@article{2021RobustNav, 
  author = {Chattopadhyay, Prithvijit and Hoffman, Judy and Mottaghi, Roozbeh and Kembhavi, Ani},
  title = {RobustNav: Towards Benchmarking Robustness in Embodied Navigation},
  year = 2021,
  journal = {International Conference in Computer Vision (ICCV)}
}

💻 Installation
📝 RobustNav Description
🖼️ Visual Corruptions
🏃 Dynamics Corruptions
📊 Dataset
🏋 Training an Agent
💪 Evaluating a Pre-Trained Agent

💻 Installation

First install Anaconda
To begin, clone this repository locally

git clone https://github.com/allenai/robustnav.git

You can then install requirements inside a conda environment by running

conda env create --file robustnav.yml --name <ENV-NAME>

where ENV-NAME is the name of the environment. The default environment name is robustnav if ENV-NAME is not specified.

Activate the conda environment by running

conda activate <ENV-NAME>

conda activate robustnav

[Optional] In case the CUDA version on your machine (if you are using linux, you might find this version by running /usr/local/cuda/bin/nvcc --version) is different from the one used in the repository, you can install your desired version by running:

conda env update --file ./conda/environment-<CUDA-VERSION>.yml --name <ENV-NAME>

where CUDA-VERSION is the specified CUDA version (this repo right now supports 9.1, 10.1 and 10.2 under the folder conda/) and ENV-NAME is the name of the project environment (robustnav or the specified name in step 3)

After installing the requirements, you should start the xserver by running this script in the background.

📝 RobustNav Description

RobustNav is a framework to evaluate pre-trained navigation agents in the presence of a wide variety of visual and dynamics corruptions. As such, this codebase supports training (in line with AllenAct) and evaluating PointNav and ObjectNav agents (either RGB and / or Depth observations) in unseen environments where visual and dynamics corruptions have been applied. For instance, in the above example, a (LoCoBot based) agent trained in a set of clean environments (see (a)), is evaluated in environments with Camera-Crack and Motion Drift as the visual and dynamics corruptions respectively (see (b) and (c)).

🖼️ Visual Corruptions

As highlighted in the figure above, RobustNav supports 7 visual corruptions -- Defocus Blur, Motion Blur, Spatter, Camera Crack, Low Lighting, Lower FOV and Speckle Noise. The above figure represents "clean" and "corrupt" egocentric RGB frames as viewed by the agent. Among these corruptions, Defocus Blur, Motion Blur, Spatter, Low Lighting and Speckle Noise are supported at 5 progressively increasing levels of severity. Defocus Blur, Spatter and Speckle Noise are akin to the visual corruptions introduced here. Note that these corruptions are applied only on the RGB observations (not Depth).

🏃 Dynamics Corruptions

As highlighted above, RobustNav includes 4 dynamics corruptions -- (a) Motion Bias (Constant), (b) Motion Bias (Stochastic), (c) Motion Drift and (d) Motor Failure. Motion Bias (Constant & Stochastic) are intended to model scene-level friction and high and low friction zones in the environment. Motion Drift models a setting where translation (forward) has a slight bias towards turning left or right. In Motor Failure, one of the rotation actions fail.

PointNav agents have the following actions available to them -- MoveAhead (0.25m), RotateLeft (30°), RotateRight (30°) and End (end an episode). ObjectNav agents additionally have access to LookUp and LookDown actions -- indicating change in agent's view above or below the horizon.

📊 Dataset

Agents in RobustNav are trained and evaluated on the RoboTHOR set of scenes. RoboTHOR consists of 60 training and 15 validation environments. Agents are trained on the train set of environments are evaluated on the validation set of environments. Evaluation episodes are present in datasets/robothor-pointnav/robustnav_eval/ for PointNav and datasets/robothor-objectnav/robustnav_eval/ for ObjectNav. For ObjectNav, we consider 12 object categories -- AlarmClock, Apple, BaseBallBat, BasketBall, Bowl, GarbageCan, HousePlant, Laptop, Mug, SprayBottle, Television and Vase.

🏋 Training An Agent

To train an agent, we rely on the experiment configs located here. Upon activating the robustnav anaconda environment, run the following command to train an agent:

python main.py \
    -o storage/<EXPERIMENT-STORAGE-DIRECTORY> \
    -b projects/robustnav_baselines/experiments/robustnav_train <EXPERIMENT-CONFIG> \
    -s <RANDOM-SEED> \
    -et <EXPERIMENT-STRING-TAG-IDENTIFIER>

For instance, to train a PointNav RGB agent, the command is:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo \
    -b projects/robustnav_baselines/experiments/robustnav_train pointnav_robothor_vanilla_rgb_resnet_ddppo \
    -s 12345 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_clean

Checkpoints over the course of training will be stored under storage/robothor-pointnav-rgb-resnetgru-ddppo/checkpoints/ and tensorboard logs will be stored under storage/robothor-pointnav-rgb-resnetgru-ddppo/tb/.

If you have Tensorboard installed, you can track training progress with

tensorboard --logdir storage/robothor-pointnav-rgb-resnetgru-ddppo/tb/

which will default to the URL http://localhost:6006/.

To see commands used to train the navigation agents considered in the paper, see train_navigation_agents.sh

💪 Evaluating A Pre-Trained Agent

To evaluate pre-trained navigation agents, first run this script to download all the checkpoints.

For evaluation, we will consider evaluating an agent under (1) clean settings, (2) under visual corruptions, (3) under dynamics corruptions and (4)under visual + dynamics corruptions. We will consider evaluating a pre-trained PointNav RGB agent as the running example.

Clean Settings

To evaluate under clean settings, run the following command:

python main.py \
    -o <METRIC-STORAGE-DIRECTORY> \
    -b projects/robustnav_baselines/experiments/robustnav_eval <EXPERIMENT-CONFIG> \
    -c <CHECKPOINT-PATH> \
    -t <CHECKPOINT-TIMESTAMP> \
    -et <EXPERIMENT-STRING-TAG-IDENTIFIER> \
    -s <RANDOM-SEED> \
    -e \
    -tsg <GPU-ID>

For a PointNav RGB agent, this is equivalent to:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_clean \
    -s 12345 \
    -e \
    -tsg 0

The output trajectories and associated metrics per episode will be stored under storage/robothor-pointnav-rgb-resnetgru-ddppo-eval/metrics/.

Visual Corruptions

For visual corruptions, when evaluating under Defocus Blur, Motion Blur, Spatter, Low Lighting and Speckle Noise, we have two additional command line arguments -vc and -vs identifying the kind and severity of the corruptions. For instance, to evaluate under Defocus Blur, the command is:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_Defocus_Blur_s5 \
    -s 12345 \
    -e \
    -tsg 0 \
    -vc Defocus_Blur \
    -vs 5

When evaluating under Lower-FOV, run:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo_fov \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_fov \
    -s 12345 \
    -e \
    -tsg 0

When evaluating under Camera-Crack, run:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo_cam_crack \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_cam_crack \
    -s 12345 \
    -e \
    -tsg 0

Dynamics Corruptions

When evaluating under Motion Bias (Constant), run:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo_dyn \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_clean_mb_const \
    -s 12345 \
    -e \
    -tsg 0 \
    -dcr \
    -ctr \
    -crt

-dcr is set to True for Motion Bias, Motion Drift and Motor Failure. -ctr is set to True for constant translation bias and -crt is set to True for constant rotation bias.

When evaluating under Motion Bias (Stochastic), run:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo_dyn \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_clean_mb_stoch \
    -s 12345 \
    -e \
    -tsg 0 \
    -dcr \
    -str \
    -srt

-str is set to True for stochastic translation bias and -srt is set to True for stochastic rotation bias.

When evaluating under Motion Drift, run:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo_dyn \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_clean_drift_deg_10 \
    -s 12345 \
    -e \
    -tsg 0 \
    -dcr \
    -dr \
    -dr_deg 10.0

-dr is set to True for motion drift and -dr_deg is set to 10.0 as the drift angle.

When evaluating under Motor Failure, run:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo_dyn \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_clean_motfail \
    -s 12345 \
    -e \
    -tsg 0 \
    -dcr \
    -mf

-mf is set to True for motor failure.

When evaluating under PyRobot noise models from here, run:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo_pyrobot_dyn \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_clean_pyrobot_ilqr_1 \
    -s 12345 \
    -e \
    -tsg 0

Note that the experiment config used for PyRobot settings is different from the ones used for Motion Bias, Motion Drift and Motor Failure. To evaluate other agents which differ either in terms of the task (PointNav→ObjectNav) or sensors (RGB→RGB-D), just pick the corresponding experiment configs and checkpoints under projects/robustnav_baselines/experiments/robustnav_eval/ and rnav_checkpoints/ respectively. These instructions are also highlighted in eval_navigation_agents.sh.

If you use the PyRobot noise models, please cite:

@article{murali2019pyrobot,
  title={Pyrobot: An open-source robotics framework for research and benchmarking},
  author={Murali, Adithyavairavan and Chen, Tao and Alwala, Kalyan Vasudev and Gandhi, Dhiraj and Pinto, Lerrel and Gupta, Saurabh and Gupta, Abhinav},
  journal={arXiv preprint arXiv:1906.08236},
  year={2019}
}

Visual + Dynamics Corruptions

To evaluate in the presence of visual and dynamics corruptions, use the additional -vc and -vs arguments to highlight the kind and severity of visual corruption in the commands used to evaluate under dynamics corruptions (above). For instance, to evaluate under Defocus Blur + Motion Drift, the command is:

python main.py \
    -o storage/robothor-pointnav-rgb-resnetgru-ddppo-eval \
    -b projects/robustnav_baselines/experiments/robustnav_eval pointnav_robothor_vanilla_rgb_resnet_ddppo_dyn \
    -c rnav_checkpoints/pnav_rgb_agent.pt \
    -t 2021-03-02_05-58-58 \
    -et rnav_pointnav_vanilla_rgb_resnet_ddppo_clean_drift_deg_10 \
    -s 12345 \
    -e \
    -tsg 0 \
    -dcr \
    -dr \
    -dr_deg 10.0 \
    -vc Defocus_Blur \
    -vs 5

To find the time-stamps associated with all the checkpoints, refer to eval_navigation_agents.sh.

robustnav's People

Contributors

Stargazers

Watchers

Forkers

prithv1 dexiongyung wujiaxu

robustnav's Issues

cannot run the PointNav expriments on a remote server(no screen)

Hi, when i ran the code according to the README on a remote server(no screen), some issures arose.
First, i run python scripts/startx.py.
Then, i run bash train_navigation_agents.sh.
While, it seems like the training didn't start, because the output info looks like it's stuck.

The output info is (NUM_PROCESSES = 6):

10/09 16:55:56 INFO: Running with args Namespace(approx_ckpt_steps_count=None, checkpoint=None, color_jitter=False, const_rotate=False, const_translate=False, deterministic_agents=False, deterministic_cudnn=False, disable_config_saving=False, disable_tensorboard=False, drift=False, drift_degrees=1.15, dyn_corr_mode=False, experiment='pointnav_robothor_vanilla_rgb_resnet_ddppo', experiment_base='projects/robustnav_baselines/experiments/robustnav_train', extra_tag='rnav_pointnav_vanilla_rgb_resnet_ddppo_clean', gp=None, log_level='info', max_sampler_processes_per_worker=None, motor_failure=False, output_dir='storage/robothor-pointnav-rgb-resnetgru-ddppo', random_crop=False, random_shift=False, restart_pipeline=False, seed=12345, skip_checkpoints=0, stoch_rotate=False, stoch_translate=False, test_dataset=None, test_date=None, test_gpus=None, training_dataset=None, validation_dataset=None, visual_corruption=None, visual_severity=0)	[main.py: 469]
10/09 16:55:57 INFO: [5]	[system.py: 128]
10/09 16:55:57 INFO: Sensor UUID is  rgb_lowres	[system.py: 128]
10/09 16:55:57 INFO: Applied corruptions are	[system.py: 128]
10/09 16:55:57 INFO: None	[system.py: 128]
10/09 16:55:57 INFO: 0	[system.py: 128]
10/09 16:55:57 INFO: Random Crop state  False	[system.py: 128]
10/09 16:55:57 INFO: Color Jitter state  False	[system.py: 128]
10/09 16:55:57 INFO: Random Translate  False	[system.py: 128]
10/09 16:55:57 INFO: Git diff saved to storage/robothor-pointnav-rgb-resnetgru-ddppo/used_configs/Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO/rnav_pointnav_vanilla_rgb_resnet_ddppo_clean/2023-10-09_16-55-57	[runner.py: 479]
10/09 16:55:57 INFO: Config files saved to storage/robothor-pointnav-rgb-resnetgru-ddppo/used_configs/Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO/rnav_pointnav_vanilla_rgb_resnet_ddppo_clean/2023-10-09_16-55-57	[runner.py: 516]
10/09 16:55:57 INFO: Using 6 train workers on devices (device(type='cuda', index=0), device(type='cuda', index=1), device(type='cuda', index=2), device(type='cuda', index=3), device(type='cuda', index=4), device(type='cuda', index=5))	[runner.py: 154]
10/09 16:56:00 INFO: train 0 args {'experiment_name': 'Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO_rnav_pointnav_vanilla_rgb_resnet_ddppo_clean', 'config': <projects.robustnav_baselines.experiments.robustnav_train.pointnav_robothor_vanilla_rgb_resnet_ddppo.PointNavS2SRGBResNetDDPPO object at 0x7fd4f24d4190>, 'results_queue': <multiprocessing.queues.Queue object at 0x7fd3a32ebf40>, 'checkpoints_queue': <multiprocessing.queues.Queue object at 0x7fd3a3288bb0>, 'checkpoints_dir': 'storage/robothor-pointnav-rgb-resnetgru-ddppo/checkpoints/Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO/rnav_pointnav_vanilla_rgb_resnet_ddppo_clean/2023-10-09_16-55-57', 'seed': 12345, 'deterministic_cudnn': False, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3a3293430>, 'num_workers': 6, 'device': device(type='cuda', index=0), 'distributed_port': 51385, 'max_sampler_processes_per_worker': None, 'initial_model_state_dict': '[SUPRESSED]', 'mode': 'train', 'worker_id': 0}	[runner.py: 208]
10/09 16:56:03 INFO: train 1 args {'experiment_name': 'Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO_rnav_pointnav_vanilla_rgb_resnet_ddppo_clean', 'config': <projects.robustnav_baselines.experiments.robustnav_train.pointnav_robothor_vanilla_rgb_resnet_ddppo.PointNavS2SRGBResNetDDPPO object at 0x7fd4f24d4190>, 'results_queue': <multiprocessing.queues.Queue object at 0x7fd367ac2f40>, 'checkpoints_queue': <multiprocessing.queues.Queue object at 0x7fd367a5fbb0>, 'checkpoints_dir': 'storage/robothor-pointnav-rgb-resnetgru-ddppo/checkpoints/Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO/rnav_pointnav_vanilla_rgb_resnet_ddppo_clean/2023-10-09_16-55-57', 'seed': 12345, 'deterministic_cudnn': False, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd367a6a430>, 'num_workers': 6, 'device': device(type='cuda', index=1), 'distributed_port': 51385, 'max_sampler_processes_per_worker': None, 'initial_model_state_dict': '[SUPRESSED]', 'mode': 'train', 'worker_id': 1}	[runner.py: 208]
10/09 16:56:06 INFO: train 2 args {'experiment_name': 'Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO_rnav_pointnav_vanilla_rgb_resnet_ddppo_clean', 'config': <projects.robustnav_baselines.experiments.robustnav_train.pointnav_robothor_vanilla_rgb_resnet_ddppo.PointNavS2SRGBResNetDDPPO object at 0x7fd4f24d4190>, 'results_queue': <multiprocessing.queues.Queue object at 0x7fd3b32ebf40>, 'checkpoints_queue': <multiprocessing.queues.Queue object at 0x7fd3b3288bb0>, 'checkpoints_dir': 'storage/robothor-pointnav-rgb-resnetgru-ddppo/checkpoints/Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO/rnav_pointnav_vanilla_rgb_resnet_ddppo_clean/2023-10-09_16-55-57', 'seed': 12345, 'deterministic_cudnn': False, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3b3293430>, 'num_workers': 6, 'device': device(type='cuda', index=2), 'distributed_port': 51385, 'max_sampler_processes_per_worker': None, 'initial_model_state_dict': '[SUPRESSED]', 'mode': 'train', 'worker_id': 2}	[runner.py: 208]
10/09 16:56:09 INFO: train 3 args {'experiment_name': 'Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO_rnav_pointnav_vanilla_rgb_resnet_ddppo_clean', 'config': <projects.robustnav_baselines.experiments.robustnav_train.pointnav_robothor_vanilla_rgb_resnet_ddppo.PointNavS2SRGBResNetDDPPO object at 0x7fd4f24d4190>, 'results_queue': <multiprocessing.queues.Queue object at 0x7fd3895faf40>, 'checkpoints_queue': <multiprocessing.queues.Queue object at 0x7fd389597bb0>, 'checkpoints_dir': 'storage/robothor-pointnav-rgb-resnetgru-ddppo/checkpoints/Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO/rnav_pointnav_vanilla_rgb_resnet_ddppo_clean/2023-10-09_16-55-57', 'seed': 12345, 'deterministic_cudnn': False, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3895a2430>, 'num_workers': 6, 'device': device(type='cuda', index=3), 'distributed_port': 51385, 'max_sampler_processes_per_worker': None, 'initial_model_state_dict': '[SUPRESSED]', 'mode': 'train', 'worker_id': 3}	[runner.py: 208]
10/09 16:56:12 INFO: train 4 args {'experiment_name': 'Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO_rnav_pointnav_vanilla_rgb_resnet_ddppo_clean', 'config': <projects.robustnav_baselines.experiments.robustnav_train.pointnav_robothor_vanilla_rgb_resnet_ddppo.PointNavS2SRGBResNetDDPPO object at 0x7fd4f24d4190>, 'results_queue': <multiprocessing.queues.Queue object at 0x7fd380544f40>, 'checkpoints_queue': <multiprocessing.queues.Queue object at 0x7fd3804e0bb0>, 'checkpoints_dir': 'storage/robothor-pointnav-rgb-resnetgru-ddppo/checkpoints/Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO/rnav_pointnav_vanilla_rgb_resnet_ddppo_clean/2023-10-09_16-55-57', 'seed': 12345, 'deterministic_cudnn': False, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3804ec430>, 'num_workers': 6, 'device': device(type='cuda', index=4), 'distributed_port': 51385, 'max_sampler_processes_per_worker': None, 'initial_model_state_dict': '[SUPRESSED]', 'mode': 'train', 'worker_id': 4}	[runner.py: 208]
10/09 16:56:16 INFO: Started 6 train processes	[runner.py: 294]
10/09 16:56:16 INFO: Using 1 valid workers on devices (device(type='cuda', index=5),)	[runner.py: 154]
10/09 16:56:16 INFO: train 5 args {'experiment_name': 'Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO_rnav_pointnav_vanilla_rgb_resnet_ddppo_clean', 'config': <projects.robustnav_baselines.experiments.robustnav_train.pointnav_robothor_vanilla_rgb_resnet_ddppo.PointNavS2SRGBResNetDDPPO object at 0x7fd4f24d5190>, 'results_queue': <multiprocessing.queues.Queue object at 0x7fd3ab2e4f40>, 'checkpoints_queue': <multiprocessing.queues.Queue object at 0x7fd3ab281bb0>, 'checkpoints_dir': 'storage/robothor-pointnav-rgb-resnetgru-ddppo/checkpoints/Pointnav-RoboTHOR-Vanilla-RGB-ResNet-DDPPO/rnav_pointnav_vanilla_rgb_resnet_ddppo_clean/2023-10-09_16-55-57', 'seed': 12345, 'deterministic_cudnn': False, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3ab28c430>, 'num_workers': 6, 'device': device(type='cuda', index=5), 'distributed_port': 51385, 'max_sampler_processes_per_worker': None, 'initial_model_state_dict': '[SUPRESSED]', 'mode': 'train', 'worker_id': 5}	[runner.py: 208]
10/09 16:56:19 INFO: Started 1 valid processes	[runner.py: 320]
10/09 16:56:19 INFO: valid 0 args {'config': <projects.robustnav_baselines.experiments.robustnav_train.pointnav_robothor_vanilla_rgb_resnet_ddppo.PointNavS2SRGBResNetDDPPO object at 0x7fd4f24d4190>, 'results_queue': <multiprocessing.queues.Queue object at 0x7fd3bbd8df70>, 'checkpoints_queue': <multiprocessing.queues.Queue object at 0x7fd3bbd29be0>, 'seed': 12345, 'deterministic_cudnn': False, 'deterministic_agents': False, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3bbd33460>, 'device': device(type='cuda', index=5), 'max_sampler_processes_per_worker': None, 'mode': 'valid', 'worker_id': 0}	[runner.py: 223]
10/09 16:56:25 INFO: Actor critic model has no attribute inverse mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute rotation mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute inverse mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute rotation mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute inverse mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute rotation mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute inverse mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute rotation mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute inverse mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute rotation mode	[system.py: 128]
10/09 16:56:25 INFO: Actor critic model has no attribute inverse mode	[system.py: 128]
10/09 16:56:25 INFO: Starting 0-th VectorSampledTask worker with args [{'scenes': ['FloorPlan_Train6_1', 'FloorPlan_Train11_5', 'FloorPlan_Train3_5', 'FloorPlan_Train7_1', 'FloorPlan_Train8_1', 'FloorPlan_Train10_3', 'FloorPlan_Train4_1', 'FloorPlan_Train12_4', 'FloorPlan_Train10_5', 'FloorPlan_Train3_2'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7fd4f24d4280>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7fd3b32ebdc0>], 'action_space': Discrete(4), 'seed': 1282648386, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.2'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3b3293430>}]	[vector_sampled_tasks.py: 344]
10/09 16:56:25 INFO: Actor critic model has no attribute rotation mode	[system.py: 128]
10/09 16:56:25 INFO: Starting 0-th VectorSampledTask worker with args [{'scenes': ['FloorPlan_Train10_1', 'FloorPlan_Train2_3', 'FloorPlan_Train2_2', 'FloorPlan_Train5_1', 'FloorPlan_Train8_4', 'FloorPlan_Train7_3', 'FloorPlan_Train3_1', 'FloorPlan_Train12_5', 'FloorPlan_Train7_5', 'FloorPlan_Train7_4'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7fd4f24d4280>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7fd367ac2dc0>], 'action_space': Discrete(4), 'seed': 43676229, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.1'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd367a6a430>}]	[vector_sampled_tasks.py: 344]
10/09 16:56:25 INFO: Starting 0-th VectorSampledTask worker with args [{'scenes': ['FloorPlan_Train8_5', 'FloorPlan_Train12_2', 'FloorPlan_Train9_1', 'FloorPlan_Train11_1', 'FloorPlan_Train4_2', 'FloorPlan_Train5_5', 'FloorPlan_Train1_2', 'FloorPlan_Train9_2', 'FloorPlan_Train1_3', 'FloorPlan_Train1_1'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7fd4f24d4280>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7fd3a32ebdc0>], 'action_space': Discrete(4), 'seed': 1789368711, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.0'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3a3293430>}]	[vector_sampled_tasks.py: 344]
10/09 16:56:25 INFO: Starting 0-th VectorSampledTask worker with args [{'scenes': ['FloorPlan_Train9_4', 'FloorPlan_Train8_3', 'FloorPlan_Train10_2', 'FloorPlan_Train5_4', 'FloorPlan_Train11_3', 'FloorPlan_Train9_3', 'FloorPlan_Train6_2', 'FloorPlan_Train4_3', 'FloorPlan_Train3_3', 'FloorPlan_Train4_5'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7fd4f24d4280>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7fd3895fadc0>], 'action_space': Discrete(4), 'seed': 1582316135, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.3'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3895a2430>}]	[vector_sampled_tasks.py: 344]
10/09 16:56:25 INFO: Starting 0-th VectorSampledTask worker with args [{'scenes': ['FloorPlan_Train6_3', 'FloorPlan_Train12_3', 'FloorPlan_Train12_1', 'FloorPlan_Train5_3', 'FloorPlan_Train3_4', 'FloorPlan_Train1_4', 'FloorPlan_Train11_2', 'FloorPlan_Train5_2', 'FloorPlan_Train2_1', 'FloorPlan_Train6_5'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7fd4f24d5280>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7fd3ab2e4dc0>], 'action_space': Discrete(4), 'seed': 1160692746, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.5'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3ab28c430>}]	[vector_sampled_tasks.py: 344]
10/09 16:56:25 INFO: Starting 0-th VectorSampledTask worker with args [{'scenes': ['FloorPlan_Train8_2', 'FloorPlan_Train9_5', 'FloorPlan_Train2_5', 'FloorPlan_Train7_2', 'FloorPlan_Train4_4', 'FloorPlan_Train11_4', 'FloorPlan_Train1_5', 'FloorPlan_Train10_4', 'FloorPlan_Train6_4', 'FloorPlan_Train2_4'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7fd4f24d4280>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7fd380544dc0>], 'action_space': Discrete(4), 'seed': 831769172, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.4'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True, 'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd3804ec430>}]	[vector_sampled_tasks.py: 344]
10/09 16:56:27 INFO: Actor critic model has no attribute inverse mode	[system.py: 128]
10/09 16:56:27 INFO: Actor critic model has no attribute rotation mode	[system.py: 128]
10/09 16:56:28 INFO: Starting 0-th SingleProcessVectorSampledTasks generator with args {'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7f46ef1bc790>, 'scenes': ['FloorPlan_Train6_1', 'FloorPlan_Train11_5', 'FloorPlan_Train3_5', 'FloorPlan_Train7_1', 'FloorPlan_Train8_1', 'FloorPlan_Train10_3', 'FloorPlan_Train4_1', 'FloorPlan_Train12_4', 'FloorPlan_Train10_5', 'FloorPlan_Train3_2'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7f474b5432e0>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7f46ef1bc5b0>], 'action_space': Discrete(4), 'seed': 1282648386, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.2'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True}	[vector_sampled_tasks.py: 975]
10/09 16:56:28 INFO: Starting 0-th SingleProcessVectorSampledTasks generator with args {'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7fd5bdcd27f0>, 'scenes': ['FloorPlan_Train6_3', 'FloorPlan_Train12_3', 'FloorPlan_Train12_1', 'FloorPlan_Train5_3', 'FloorPlan_Train3_4', 'FloorPlan_Train1_4', 'FloorPlan_Train11_2', 'FloorPlan_Train5_2', 'FloorPlan_Train2_1', 'FloorPlan_Train6_5'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7fd60907d2e0>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7fd5bdcd2610>], 'action_space': Discrete(4), 'seed': 1160692746, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.5'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True}	[vector_sampled_tasks.py: 975]
10/09 16:56:28 INFO: Starting 0-th SingleProcessVectorSampledTasks generator with args {'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7f812fd80760>, 'scenes': ['FloorPlan_Train10_1', 'FloorPlan_Train2_3', 'FloorPlan_Train2_2', 'FloorPlan_Train5_1', 'FloorPlan_Train8_4', 'FloorPlan_Train7_3', 'FloorPlan_Train3_1', 'FloorPlan_Train12_5', 'FloorPlan_Train7_5', 'FloorPlan_Train7_4'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7f81b2c202e0>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7f812fd80580>], 'action_space': Discrete(4), 'seed': 43676229, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.1'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True}	[vector_sampled_tasks.py: 975]
10/09 16:56:28 INFO: Camera-Crack  False	[system.py: 128]
10/09 16:56:28 INFO: Motor Failure Mode (Left / Right) is  False	[system.py: 128]
10/09 16:56:28 INFO: Constant (but Uniform) translate friction False	[system.py: 128]
10/09 16:56:28 INFO: Constant (but Uniform) Rotate friction False	[system.py: 128]
10/09 16:56:28 INFO: Stoch translate friction False	[system.py: 128]
10/09 16:56:28 INFO: Stoch Rotate friction False	[system.py: 128]
10/09 16:56:28 INFO: Drift Mode is  False	[system.py: 128]
10/09 16:56:28 INFO: Camera-Crack  False	[system.py: 128]
10/09 16:56:28 INFO: Motor Failure Mode (Left / Right) is  False	[system.py: 128]
10/09 16:56:28 INFO: Constant (but Uniform) translate friction False	[system.py: 128]
10/09 16:56:28 INFO: Constant (but Uniform) Rotate friction False	[system.py: 128]
10/09 16:56:28 INFO: Stoch translate friction False	[system.py: 128]
10/09 16:56:28 INFO: Stoch Rotate friction False	[system.py: 128]
10/09 16:56:28 INFO: Drift Mode is  False	[system.py: 128]
10/09 16:56:28 INFO: Starting 0-th SingleProcessVectorSampledTasks generator with args {'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7f82c6b556d0>, 'scenes': ['FloorPlan_Train9_4', 'FloorPlan_Train8_3', 'FloorPlan_Train10_2', 'FloorPlan_Train5_4', 'FloorPlan_Train11_3', 'FloorPlan_Train9_3', 'FloorPlan_Train6_2', 'FloorPlan_Train4_3', 'FloorPlan_Train3_3', 'FloorPlan_Train4_5'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7f8349f262e0>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7f82c6b554f0>], 'action_space': Discrete(4), 'seed': 1582316135, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.3'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True}	[vector_sampled_tasks.py: 975]
10/09 16:56:28 INFO: Starting 0-th SingleProcessVectorSampledTasks generator with args {'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7f9173fbe700>, 'scenes': ['FloorPlan_Train8_5', 'FloorPlan_Train12_2', 'FloorPlan_Train9_1', 'FloorPlan_Train11_1', 'FloorPlan_Train4_2', 'FloorPlan_Train5_5', 'FloorPlan_Train1_2', 'FloorPlan_Train9_2', 'FloorPlan_Train1_3', 'FloorPlan_Train1_1'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7f92403352e0>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7f9173fbe520>], 'action_space': Discrete(4), 'seed': 1789368711, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.0'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True}	[vector_sampled_tasks.py: 975]
10/09 16:56:28 INFO: Starting 0-th SingleProcessVectorSampledTasks generator with args {'mp_ctx': <multiprocessing.context.ForkServerContext object at 0x7f1a690c56a0>, 'scenes': ['FloorPlan_Train8_2', 'FloorPlan_Train9_5', 'FloorPlan_Train2_5', 'FloorPlan_Train7_2', 'FloorPlan_Train4_4', 'FloorPlan_Train11_4', 'FloorPlan_Train1_5', 'FloorPlan_Train10_4', 'FloorPlan_Train6_4', 'FloorPlan_Train2_4'], 'max_steps': 500, 'sensors': [<allenact_plugins.ithor_plugin.ithor_sensors.RGBSensorThor object at 0x7f1a9542f2e0>, <allenact_plugins.robothor_plugin.robothor_sensors.GPSCompassSensorRoboThor object at 0x7f1a690c54c0>], 'action_space': Discrete(4), 'seed': 831769172, 'deterministic_cudnn': False, 'rewards_config': {'step_penalty': -0.01, 'goal_success_reward': 10.0, 'failed_stop_reward': 0.0, 'reached_max_steps_reward': 0.0, 'shaping_weight': 1.0}, 'env_args': {'width': 400, 'height': 300, 'continuousMode': True, 'applyActionNoise': True, 'agentType': 'stochastic', 'rotateStepDegrees': 30.0, 'gridSize': 0.25, 'snapToGrid': False, 'agentMode': 'locobot', 'fieldOfView': 63.453048374758716, 'include_private_scenes': False, 'renderDepthImage': False, 'x_display': '0.4'}, 'scene_directory': '/data1/home/robustnav/datasets/robothor-pointnav/train', 'loop_dataset': True, 'allow_flipping': True}	[vector_sampled_tasks.py: 975]
10/09 16:56:28 INFO: Camera-Crack  False	[system.py: 128]
10/09 16:56:28 INFO: Motor Failure Mode (Left / Right) is  False	[system.py: 128]
10/09 16:56:28 INFO: Constant (but Uniform) translate friction False	[system.py: 128]
10/09 16:56:28 INFO: Constant (but Uniform) Rotate friction False	[system.py: 128]
10/09 16:56:28 INFO: Stoch translate friction False	[system.py: 128]
10/09 16:56:28 INFO: Stoch Rotate friction False	[system.py: 128]
10/09 16:56:28 INFO: Drift Mode is  False	[system.py: 128]
10/09 16:56:29 INFO: Camera-Crack  False	[system.py: 128]
10/09 16:56:29 INFO: Motor Failure Mode (Left / Right) is  False	[system.py: 128]
10/09 16:56:29 INFO: Constant (but Uniform) translate friction False	[system.py: 128]
10/09 16:56:29 INFO: Constant (but Uniform) Rotate friction False	[system.py: 128]
10/09 16:56:29 INFO: Stoch translate friction False	[system.py: 128]
10/09 16:56:29 INFO: Stoch Rotate friction False	[system.py: 128]
10/09 16:56:29 INFO: Drift Mode is  False	[system.py: 128]
10/09 16:56:29 INFO: Camera-Crack  False	[system.py: 128]
10/09 16:56:29 INFO: Motor Failure Mode (Left / Right) is  False	[system.py: 128]
10/09 16:56:29 INFO: Constant (but Uniform) translate friction False	[system.py: 128]
10/09 16:56:29 INFO: Constant (but Uniform) Rotate friction False	[system.py: 128]
10/09 16:56:29 INFO: Stoch translate friction False	[system.py: 128]
10/09 16:56:29 INFO: Stoch Rotate friction False	[system.py: 128]
10/09 16:56:29 INFO: Drift Mode is  False	[system.py: 128]
10/09 16:56:29 INFO: Camera-Crack  False	[system.py: 128]
10/09 16:56:29 INFO: Motor Failure Mode (Left / Right) is  False	[system.py: 128]
10/09 16:56:29 INFO: Constant (but Uniform) translate friction False	[system.py: 128]
10/09 16:56:29 INFO: Constant (but Uniform) Rotate friction False	[system.py: 128]
10/09 16:56:29 INFO: Stoch translate friction False	[system.py: 128]
10/09 16:56:29 INFO: Stoch Rotate friction False	[system.py: 128]
10/09 16:56:29 INFO: Drift Mode is  False	[system.py: 128]
Found path: /data1/home/.ai2thor/releases/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e
Found path: /data1/home/.ai2thor/releases/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e
Found path: /data1/home/.ai2thor/releases/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e
Found path: /data1/home/.ai2thor/releases/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e
Found path: /data1/home/.ai2thor/releases/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e
Found path: /data1/home/.ai2thor/releases/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e/thor-Linux64-8f5a485b47864604795b3a57c062ada8c0bd1c3e

And the nvidia-smi is (6 A100 GPU):

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|    0   N/A  N/A   1323988      C   python                          19738MiB |
|    0   N/A  N/A   2670163      G   /usr/lib/xorg/Xorg                  8MiB |
|    0   N/A  N/A   2670544      G   /usr/lib/xorg/Xorg                 17MiB |
|    0   N/A  N/A   3035634      C   Train-0                          2172MiB |
|    1   N/A  N/A   2670163      G   /usr/lib/xorg/Xorg                  8MiB |
|    1   N/A  N/A   2670544      G   /usr/lib/xorg/Xorg                 17MiB |
|    1   N/A  N/A   3035851      C   Train-1                          2172MiB |
|    2   N/A  N/A   2670163      G   /usr/lib/xorg/Xorg                  8MiB |
|    2   N/A  N/A   2670544      G   /usr/lib/xorg/Xorg                 17MiB |
|    2   N/A  N/A   3036119      C   Train-2                          2172MiB |
|    3   N/A  N/A   2670163      G   /usr/lib/xorg/Xorg                  8MiB |
|    3   N/A  N/A   2670544      G   /usr/lib/xorg/Xorg                 17MiB |
|    3   N/A  N/A   3036385      C   Train-3                          2172MiB |
|    4   N/A  N/A   2670163      G   /usr/lib/xorg/Xorg                  8MiB |
|    4   N/A  N/A   2670544      G   /usr/lib/xorg/Xorg                 17MiB |
|    4   N/A  N/A   3036652      C   Train-4                          2172MiB |
|    5   N/A  N/A   2670163      G   /usr/lib/xorg/Xorg                  8MiB |
|    5   N/A  N/A   2670544      G   /usr/lib/xorg/Xorg                 17MiB |
|    5   N/A  N/A   3036922      C   Train-5                          2172MiB |
|    5   N/A  N/A   3037196      C   Valid-0                          2172MiB |

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.