Files

Adam Gleave f272969325 GAIL: bugfix in dataset loading (#447 )

* Fix silly typo

* Replace ad-hoc function with NumPy code

2018-07-06 16:12:14 -07:00

dataset

GAIL: bugfix in dataset loading (#447 )

2018-07-06 16:12:14 -07:00

result

Add files via upload

2017-12-12 19:03:42 -08:00

__init__.py

add gail, file_writer for tf.summary, and allow specifying var_list for tf.train.Saver

2017-12-03 01:49:42 -08:00

adversary.py

fix gail tf_util usage

2018-02-05 07:51:27 -08:00

behavior_clone.py

fix relative import

2018-01-12 15:12:45 -08:00

gail-eval.py

fix relative import

2018-01-12 15:12:45 -08:00

mlp_policy.py

fix gail tf_util usage

2018-02-05 07:51:27 -08:00

README.md

fix typo

2018-01-21 22:13:01 -08:00

run_mujoco.py

fix gail tf_util usage

2018-02-05 07:51:27 -08:00

statistics.py

add gail, file_writer for tf.summary, and allow specifying var_list for tf.train.Saver

2017-12-03 01:49:42 -08:00

trpo_mpi.py

fix gail tf_util usage

2018-02-05 07:51:27 -08:00

README.md

Generative Adversarial Imitation Learning (GAIL)

Original paper: https://arxiv.org/abs/1606.03476

For results benchmarking on MuJoCo, please navigate to here

If you want to train an imitation learning agent

Step 1: Download expert data

Download the expert data into ./data, download link

Step 2: Run GAIL

Run with single thread:

python -m baselines.gail.run_mujoco

Run with multiple threads:

mpirun -np 16 python -m baselines.gail.run_mujoco

See help (-h) for more options.

In case you want to run Behavior Cloning (BC)

python -m baselines.gail.behavior_clone

See help (-h) for more options.

Contributing

Bug reports and pull requests are welcome on GitHub at https://github.com/openai/baselines/pulls.

Maintainers

Yuan-Hong Liao, andrewliao11_at_gmail_dot_com
Ryan Julian, ryanjulian_at_gmail_dot_com

Others

Thanks to the open source:

@openai/imitation
@carpedm20/deep-rl-tensorflow