Commit Graph

2470 Commits

Author SHA1 Message Date
Jonas Schneider
6bb2d56266 Minor Python3 compat fixes 2016-05-10 17:05:47 +02:00
Jonas Schneider
cda4518b1e Bump mujoco-py for Python3 compat 2016-05-10 17:05:04 +02:00
Greg Brockman
5fc9798fe9 Add swig 2016-05-09 23:05:52 -07:00
Greg Brockman
86a189faf6 Add box2d to README 2016-05-09 23:00:28 -07:00
Greg Brockman
e53694f655 Add box2d extras 2016-05-09 22:59:09 -07:00
Greg Brockman
21aca1e9bd Register new Box2d tasks 2016-05-09 22:58:14 -07:00
Greg Brockman
afdc764b55 Merge branch 'box2d-v2' from olegklimov 2016-05-09 22:50:17 -07:00
Greg Brockman
6628be88ac Remove cartpole swingup, per @joschu's comments
https://github.com/openai/gym/pull/54#issuecomment-216973890
2016-05-09 22:50:03 -07:00
Greg Brockman
beccaf3498 Register NChain and Blackjack 2016-05-09 22:10:50 -07:00
Alex Ray
5efb1c37a9 Blackjack environment from Sutton & Barto textbook (#60)
* blackjack environment from sutton & barto textbook

* blackjack: dumb agents can hit at 21

* blackjack: add natural (Casino Rules) flag

* blackjack: style and whitespace fixes

* blackjack: simplify reward calculation
2016-05-09 22:05:56 -07:00
Alex Ray
db08326d46 n-Chain environment added (#61)
* n-Chain environment added

* nchain: match original paper's timestep limit
2016-05-09 22:04:34 -07:00
Shu Shen
168f25b976 Fix Python3 compatibility in Go env (#64)
Under Python3, user inputs are in string format and needs be
converted
into bytes before passing to pachi-py. The returned __repr__ from
pachi-py for the boards are bytes and needs be converted into string
for
line breaks to work.

Also fixed raw_input and print functions in play_go under
examples/scripts with six package.
2016-05-09 19:18:55 -07:00
Greg Brockman
a20719c8e3 Revert "Feature/len (#68)"
This reverts commit 705d024993.
2016-05-09 18:34:44 -07:00
Josh Marlow
7908761a60 Removed legacy super() rendering calls (#78) 2016-05-09 18:06:48 -07:00
moto
705d024993 Feature/len (#68)
* Add __len__ to discrete

* Add __len__ to tuple
2016-05-09 17:59:55 -07:00
Josh Marlow
9529fa731b Replaced is string comparison with == (#77) 2016-05-09 17:51:04 -07:00
Greg Brockman
17f4de30a3 Add __init__.py to tests 2016-05-09 17:38:19 -07:00
Greg Brockman
bd759b23f3 Add Taxi-v1 description 2016-05-09 17:31:01 -07:00
Greg Brockman
f8429d825d Import descriptions and background 2016-05-09 16:35:23 -07:00
John Schulman
fcff2a6760 fix taxi-v1 (issue #72)
- disallow start location = goal location
- north/south swapped in descriptions
2016-05-08 20:55:03 -04:00
Greg Brockman
81a4c3e57c Clarify reward docstring
Closes #70
2016-05-08 13:20:01 -07:00
Greg Brockman
97bcc5b702 Add render close=True to tests 2016-05-07 22:58:44 -07:00
John Schulman
69ef2a76f3 use raw_input instead of opencv 2016-05-07 21:01:05 -04:00
John Schulman
efb0a45941 fix taxi (upgrade -> v1). non-functional changes to frozen lake 2016-05-07 20:52:51 -04:00
Greg Brockman
322433ecff video_recorder: Check if not enabled right away
This avoids a potential logger.info call if not enabled
2016-05-07 11:45:42 -07:00
Greg Brockman
b37495355e Handle deprecated envs better 2016-05-06 22:26:40 -07:00
Greg Brockman
8781f6d623 Fix flushing of final episode in monitor
Thanks @JKCooper2.

We also change to getting the PID at monitor construction time, rather
than at runtime. This means you need to start your environments
post-fork, which should be fine.
2016-05-06 22:00:29 -07:00
Greg Brockman
21169ef620 Add TODO 2016-05-06 18:23:08 -07:00
Greg Brockman
9984589731 Improve score_from_local implementation (#66)
* Make sure that a callable is passed to start

* Improve autoflushing for score calculation

* Write stats and manifests using proper atomic_writes
2016-05-06 18:19:16 -07:00
JKCooper2
95a0151f13 Issue 45 - Easily return environment score values (#57)
* Set restriction on selected actions

* Used self.action_space instead of custom set

* Move action validation to core.py

* Added env.score() function to return current score

* Set up multi monitor scoring

* Removed unneccesary package inclusions

* Monitor writes scores automatically. Video callable can now use monitor_id

* Monitor ID not necessary for video filtering

* Fix so final stats get written when env.reset() doesn't happen

* gitignore PyCharm Project Files
2016-05-06 17:38:42 -07:00
Alex Ray
9a0a1af5b5 tuple spaces will consider lists for contains check (#63) 2016-05-06 15:46:11 -07:00
Philip Paquette
78d853a2f3 Fixed step return objects in README.rst (#58) 2016-05-04 16:07:32 -04:00
Jonas Schneider
4519a6ffe3 Warn instead of raising on invalid action 2016-05-03 22:27:26 -04:00
Jonas Schneider
618c7fda5e Don't break when passing strange values into DiscreteSpace#contains 2016-05-03 22:27:06 -04:00
Jonas Schneider
fad0065931 Call _step instead of step when fake-stepping a mujoco env on initialize 2016-05-03 22:20:41 -04:00
JKCooper2
3c983b9f1d Set restriction on selected actions for MountainCar-v0 (#47)
* Set restriction on selected actions

* Used self.action_space instead of custom set

* Move action validation to core.py
2016-05-03 21:40:24 -04:00
222464
9a50174753 Added PGE to environments (#55) 2016-05-03 16:42:52 -04:00
Oleg Klimov
3b19acdfce Box2d initial, second attempt 2016-05-03 22:27:42 +03:00
Botev
e7f7741548 Same fix for Go for StringIO 2016-05-03 20:13:05 +01:00
Botev
c62b2da337 A few compatibility issues with python3 resolved.
Fixed lot's of issues with the HexEnv.
Added Hex9x9-v0 to registry
2016-05-03 20:10:00 +01:00
Nick Pawlowski
9e716416e1 fixed bug (frame_shape -> frame.shape) (#50) 2016-05-03 11:39:50 -04:00
Jonas Schneider
f478aa7971 Fix PR tests 2016-05-03 11:09:15 -04:00
Shubham Dokania
a065d5ce7b Fixed typo (#49)
fix 'outut' to 'output'
2016-05-03 10:36:00 -04:00
Oleg Klimov
386096f60a rendering.py: 'color' keyword argument handling fixed 2016-05-03 12:07:14 +03:00
John Schulman
b69df1b5f3 fix subsampling of videos 2016-05-02 22:43:17 -07:00
Tambet Matiisen
cd65b7ecd0 Added Simple DQN. (#46) 2016-05-02 15:37:54 -04:00
Greg Brockman
8baa58c3e6 Skip deprecated envs 2016-05-02 14:49:33 -04:00
Greg Brockman
ddd014f97d Add back registration for deprecated envs 2016-05-02 14:33:55 -04:00
Greg Brockman
6f83b1d810 Bump version since we upgraded all MuJoCo envs 2016-05-02 11:31:14 -04:00
caktux
8ee65e464f pass Travis environment variables to tox for PRs (#37) 2016-05-01 23:59:44 -04:00