Comments (3)
base_dqn uses 10k action during evaluation. We did a sweep over action-to-rank on the validation set and found that the optimal number of actions depends on the generalization settings due to overcrowdness problem. See lines 145-150 in run_experiment.py:
dqn_ranks = dict(
ball_cross_template='--dqn-rank-size=1000',
ball_within_template='--dqn-rank-size=10000',
two_balls_cross_template='--dqn-rank-size=100000',
two_balls_within_template='--dqn-rank-size=100000',
)
To get the final results you need to run final
arg-generator
. It will take the pretrained DQN from base_dqn
and use it to do eval with the optimal number of actions.
from phyre.
Let me get things straight, first you ran with those settings:
dqn_ranks = dict(
ball_cross_template='--dqn-rank-size=1000',
ball_within_template='--dqn-rank-size=10000',
two_balls_cross_template='--dqn-rank-size=100000',
two_balls_within_template='--dqn-rank-size=100000',
)
Afterward, you ran another run to find the optimal amount of actions you better rank?
from phyre.
The full sequence of experiments is listed in agents/train_all_baseline.sh.
First we train a DQN on 3 dev-folds. Then we use then to rank different number of actions and measure AUCCESS:
python $RUN_EXPERIMENT_SCRIPT --use-test-split 0 --arg-generator base_dqn --num-seeds $DEV_SEEDS
python $RUN_EXPERIMENT_SCRIPT --use-test-split 0 --arg-generator rank_and_online_sweep --num-seeds $DEV_SEEDS
Then we manually chose the best number of actions to rank (see figure 4 in the paper). These values are used for get the final numbers:
python $RUN_EXPERIMENT_SCRIPT --use-test-split 1 --arg-generator base_dqn --num-seeds $FINAL_SEEDS
wait_for_results "results/final/$DQN_BASE_NAME" $FINAL_SEEDS
python $RUN_EXPERIMENT_SCRIPT --use-test-split 1 --arg-generator finals --num-seeds $FINAL_SEEDS
The first command trains DQN on the final (non-dev) folds (and ranks default 10k during evaluation, but it doesn’t matter as it’s ignored). The second command use the pre-trained checkpoints to rank optimal number of actions for each evaluation setting. It also evaluates other baseline algorithms (like MEM) on the final folds. That’s why these 2 commands are separate.
You can see what exactly each arg-generator
command do in agents/run_experiment.py
.
from phyre.
Related Issues (20)
- phyre.initialize_simulator() is too slow HOT 3
- object-based knowledge representation HOT 3
- Installing on Mac via pip limited to platform = macosx_10_0 HOT 2
- installation from source failed HOT 4
- incorrect value/need clarification for sim.initial_featurized_objects[0].Xs and Ys HOT 2
- Fb
- Cross-template folds never contain template 6 in test or dev template sets (10 folds) HOT 1
- player.phyre.ai down HOT 1
- Error when running 01_phyre_intro notebook HOT 3
- Python 3.8 Version HOT 4
- Is there a plan to provide a "gym" interface? HOT 1
- Possible issue in eval_loss
- The demo section in the website is not working HOT 2
- Fails to build with missing files HOT 1
- Unable to build from source HOT 1
- static objects out of bound HOT 1
- An error occurs in the tutorial colab file.
- How is the simulated video length related to the object states? HOT 3
- Missing "task_ids" in the two ball game cache. HOT 1
- Possible problem with ball diameter
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.
from phyre.