Files

pzhokhov cd375ab209 update readmes (#514 )

* update per-algorithm READMEs to reflect new way of running algorithms

* adding a link to repo-wide README

* updated README files and deepq.train_cartpole example

2018-08-16 14:53:49 -07:00

__init__.py

Add ACER, PPO2, and results_plotter.py

2017-11-16 10:02:32 -08:00

defaults.py

refactor a2c, acer, acktr, ppo2, deepq, and trpo_mpi (#490 )

2018-08-13 09:56:44 -07:00

ppo2.py

refactor a2c, acer, acktr, ppo2, deepq, and trpo_mpi (#490 )

2018-08-13 09:56:44 -07:00

README.md

update readmes (#514 )

2018-08-16 14:53:49 -07:00

README.md

PPO2

Original paper: https://arxiv.org/abs/1707.06347
Baselines blog post: https://blog.openai.com/openai-baselines-ppo/
python -m baselines.run --alg=ppo2 --env=PongNoFrameskip-v4 runs the algorithm for 40M frames = 10M timesteps on an Atari Pong. See help (-h) for more options.
python -m baselines.run --alg=ppo2 --env=Ant-v2 --num_timesteps=1e6 runs the algorithm for 1M frames on a Mujoco Ant environment.
also refer to the repo-wide README.md