erenulu2020 Goto Github PK

arnold

Arnold - DOOM Agent

attention-toad

Bickford Smith, Roads, Luo, Love (2021). Understanding top-down attention using task-oriented ablation design. arXiv:2106.11339.

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

deep_reinforcement_learning_course

Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch

deeprl-agents

A set of Deep Reinforcement Learning Agents implemented in Tensorflow.

doomreinforcementlearning

doorgym

Open source domain randomized door opening training environment

garage

A toolkit for reproducible reinforcement learning research.

keras-rl

Deep Reinforcement Learning for Keras.

kerasrl-openai-atari-spaceinvadersv0

A notebook walking through how to use Keras RL to solve Atari environments.

lab

A customisable 3D platform for agent-based AI research

mariorl

obstacle-tower-env

Obstacle Tower Environment

openaipong-dqn

Solving Atari Pong Game w/ Duel Double DQN in Pytorch

pops

PoPS algorithm

pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

reinforcement_learning

Reinforcement learning tutorials

reinforcementlearningcourse

sam

Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model. IEEE Transactions on Image Processing (2018)

sample-factory

High throughput asynchronous reinforcement learning

scalable_agent

A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

stella

A multi-platform Atari 2600 Emulator

tensorflowkeras-reinforcementlearning

A tutorial walking through the use of Keras-RL for reinforcement learning with OpenAI gym.

unreal

Reinforcement learning with unsupervised auxiliary tasks

unrealwithattention

Attend Before you Act: Leveraging human visual attention for continual learning

vizdoom

Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information. :godmode: