Commit Graph

21 Commits

Author SHA1 Message Date
Peter Zhokhov
b222dd0610 updated links in README to point to master 2018-08-13 16:01:24 -07:00
pzhokhov
1870685071 Publish benchmark results (#502)
* updated benchmark pages with final rewards

* use htmlpreview to render pages

* use htmlpreview to render pages

* use htmlpreview to render pages

* updated README to reflect ppo1 being obsolete

* removed navbars from published benchmark pages

* fixed link in README
2018-08-13 15:59:43 -07:00
pzhokhov
8c2aea2add refactor a2c, acer, acktr, ppo2, deepq, and trpo_mpi (#490)
* exported rl-algs

* more stuff from rl-algs

* run slow tests

* re-exported rl_algs

* re-exported rl_algs - fixed problems with serialization test and test_cartpole

* replaced atari_arg_parser with common_arg_parser

* run.py can run algos from both baselines and rl_algs

* added approximate humanoid reward with ppo2 into the README for reference

* dummy commit to RUN BENCHMARKS

* dummy commit to RUN BENCHMARKS

* dummy commit to RUN BENCHMARKS

* dummy commit to RUN BENCHMARKS

* very dummy commit to RUN BENCHMARKS

* serialize variables as a dict, not as a list

* running_mean_std uses tensorflow variables

* fixed import in vec_normalize

* dummy commit to RUN BENCHMARKS

* dummy commit to RUN BENCHMARKS

* flake8 complaints

* save all variables to make sure we save the vec_normalize normalization

* benchmarks on ppo2 only RUN BENCHMARKS

* make_atari_env compatible with mpi

* run ppo_mpi benchmarks only RUN BENCHMARKS

* hardcode names of retro environments

* add defaults

* changed default ppo2 lr schedule to linear RUN BENCHMARKS

* non-tf normalization benchmark RUN BENCHMARKS

* use ncpu=1 for mujoco sessions - gives a bit of a performance speedup

* reverted running_mean_std to user property decorators for mean, var, count

* reverted VecNormalize to use RunningMeanStd (no tf)

* reverted VecNormalize to use RunningMeanStd (no tf)

* profiling wip

* use VecNormalize with regular RunningMeanStd

* added acer runner (missing import)

* flake8 complaints

* added a note in README about TfRunningMeanStd and serialization of VecNormalize

* dummy commit to RUN BENCHMARKS

* merged benchmarks branch
2018-08-13 09:56:44 -07:00
pzhokhov
24fe3d6576 Import internal repo (#409)
* import rl-algs from 2e3a166 commit

* extra import of the baselines badge

* exported commit with identity test

* proper rng seeding in the test_identity
2018-05-21 15:24:00 -07:00
pzhokhov
9cf95a0054 setup travis ci build (#388)
* simple .travis.yml file

* added static syntax checks of common to .travis.yml

* dockerizing the build

* fix Dockerfile, adding build shield

* cleaning up workdir in Dockerfile and .travis.yml

* .travis.yml fixed common -> baselines/common for style check
2018-05-03 09:43:28 -07:00
pzhokhov
2b0283b9db Readme.md detailed installation instructions (#377)
* changes to README.md files with more detailed installation instructions

* md-fying the changes better

* link on the word homebrew in readme.md

* typos in README.md

* README.md

* removed extra comma sign

* removed sudo from brew command
2018-04-25 17:40:48 -07:00
Matthias Plappert
b71152eea0 Adds support for Hindsight Experience Replay (HER) (#299)
* Add Hindsight Experience Replay (HER)

* Minor improvements
2018-02-26 17:40:16 +01:00
John Schulman
459f007bcc Merge pull request #260 from uidilr/master
Add GAIL
2018-01-25 20:54:20 -08:00
John Schulman
9fa8e1baf1 Lots of cleanups
Fixes for new gym version
Add @olegklimov and @unixpickle to authors list
2018-01-25 18:54:24 -08:00
Yusuke Nakata
d8cce2309f Add GAIL 2018-01-23 12:02:03 +09:00
John Schulman
2dd7d307d7 Add ACER, PPO2, and results_plotter.py 2017-11-16 10:02:32 -08:00
John Schulman
bb40378118 change atari preprocessing to use faster opencv
some logger changes
2017-10-25 09:21:29 -04:00
John Schulman
aa6e58bdf1 fix readmes 2017-08-27 22:22:14 -07:00
John Schulman
3f676f7d1e ACKTR + A2C 2017-08-18 09:25:39 -07:00
Matthias Plappert
882251878f Parameter space noise for DQN and DDPG (#75)
* Export param noise

* Update documentation

* Final finishing touches
2017-07-27 08:10:59 -07:00
Jonas Schneider
5dc00628fe readme fiddling 2017-07-20 09:00:24 -07:00
John Schulman
da99706046 ppo and trpo 2017-07-20 08:52:35 -07:00
cxx
5e73387494 Fix README since BreakOut pretrained model doesn't match the correct tensor shape. Therefore, Pong is used instead. 2017-06-16 15:38:42 +08:00
Tiago Carvalho
1f3c3e33e7 Update README.md 2017-05-31 12:14:28 +01:00
Olivier Moindrot
d2c51f5933 Correct path to script "download_model"
`python -m baselines.deepq.experiments.download_model` becomes `python -m baselines.deepq.experiments.atari.download_model`
2017-05-24 13:13:30 -07:00
Szymon Sidor
958810ed1e Initial commit 2017-05-24 02:34:20 -07:00