Files

pzhokhov 5622a09fa4 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

ACKTR + A2C

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

acktr_cont.py

Lots of cleanups

2018-01-25 18:54:24 -08:00

acktr_disc.py

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

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

acktr.py

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

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

kfac_utils.py

Lots of cleanups

2018-01-25 18:54:24 -08:00

kfac.py

export: fix accidental rename

2018-02-14 22:01:16 -08:00

policies.py

Lots of cleanups

2018-01-25 18:54:24 -08:00

README.md

update readmes (#514 )

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

run_atari.py

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

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

run_mujoco.py

Lots of cleanups

2018-01-25 18:54:24 -08:00

utils.py

Lots of cleanups

2018-01-25 18:54:24 -08:00

value_functions.py

Lots of cleanups

2018-01-25 18:54:24 -08:00

README.md

ACKTR

Original paper: https://arxiv.org/abs/1708.05144
Baselines blog post: https://blog.openai.com/baselines-acktr-a2c/
python -m baselines.run --alg=acktr --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