Files

tanzhenyu d1a05a0dd2 Baselines for Tensorflow 2.0. (#978 )

* Baselines for Tensorflow 2.0.

Please do note that:
1. ACER, ACKTR, GAIL is still under development by external
contributors.
2. HER is still under development by tanzheny@google.com.

* Some cleanup.

* Addressing some comments.

2019-08-08 11:03:17 -07:00

__init__.py

ACKTR + A2C

2017-08-18 09:25:39 -07:00

a2c.py

Baselines for Tensorflow 2.0. (#978 )

2019-08-08 11:03:17 -07:00

README.md

Wrote some comments to explain the A2C and PPO2 implementation (#607 )

2018-09-21 13:12:31 -07:00

runner.py

Baselines for Tensorflow 2.0. (#978 )

2019-08-08 11:03:17 -07:00

utils.py

Baselines for Tensorflow 2.0. (#978 )

2019-08-08 11:03:17 -07:00

README.md

A2C

Original paper: https://arxiv.org/abs/1602.01783
Baselines blog post: https://blog.openai.com/baselines-acktr-a2c/
python -m baselines.run --alg=a2c --env=PongNoFrameskip-v4 runs the algorithm for 40M frames = 10M timesteps on an Atari Pong. See help (-h) for more options
also refer to the repo-wide README.md

Files

run_atari: file used to run the algorithm.
policies.py: contains the different versions of the A2C architecture (MlpPolicy, CNNPolicy, LstmPolicy...).
a2c.py: - Model : class used to initialize the step_model (sampling) and train_model (training)
- learn : Main entrypoint for A2C algorithm. Train a policy with given network architecture on a given environment using a2c algorithm.
runner.py: class used to generates a batch of experiences