Skip to content

Pull requests: openai/baselines

New pull request New
25 Open 109 Closed
25 Open 109 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix wrong docstring arg name
#1237 opened Aug 23, 2024 by kit1980 Loading…
default max_episode_steps to 27K (108K frames) in make_atari function
#1235 opened Aug 1, 2024 by rajdeepsh Loading…
1
numpy's np.bool is deprecated
#1230 opened May 23, 2024 by xan3c Loading…
Fix bug in GAIL update
#425 opened Jun 7, 2018 by Kelym Loading…
Add pdfromlatent to MultiCategoricalPdType; update deprecated tf functions
#424 opened Jun 7, 2018 by andytwigg Contributor Loading…
3
arr[end] was excluded when end is not None
#375 opened Apr 21, 2018 by royf Loading…
Add support for custom implementations of logger format outputs
#363 opened Apr 13, 2018 by Ajk4 Loading…
fix observation normalization bug for GAIL
#333 opened Mar 16, 2018 by andrewliao11 Contributor Loading…
bug fix in eval_env for DDPG
#328 opened Mar 14, 2018 by manantomar Loading…
10
Replaced missing scope functions
#283 opened Feb 9, 2018 by bbueno5000 Loading…
Rainbow based on openai baselines.[Please comment]
#251 opened Jan 12, 2018 by cxxgtxy Contributor Loading…
4
A2C, PPO2, ACKTR refactor (WIP)
#233 opened Dec 16, 2017 by kengz Loading…
4 of 8 tasks
3
fix deepq's print_freq bug
#219 opened Nov 23, 2017 by sajadn Loading…
Fix bench monitor incompatibility with dqn train.
#218 opened Nov 23, 2017 by cxxgtxy Contributor Loading…
1
Snapshot and Evaluation for a2c
#207 opened Nov 16, 2017 by BlGene Loading…
Added ability to save and restore the trained model states for PPO.
#169 opened Oct 14, 2017 by praveen-palanisamy Loading…
Derive schedules from the Schedule base class
#163 opened Oct 10, 2017 by pxc Loading…
Allow callback in acktr to use locals and globals
#150 opened Sep 28, 2017 by bjkomer Contributor Loading…
Fixed doc in deepq/replay_buffer.py
#141 opened Sep 16, 2017 by juliuskunze Loading…
Added script for roboschool support
#138 opened Sep 15, 2017 by Santara Loading…
Generalized advantages for a2c. Kept lambda=1 by default.
#133 opened Sep 12, 2017 by bhatiaabhinav Contributor Loading…
Fix meanlosses initialization.
#129 opened Sep 11, 2017 by hamzamerzic Contributor Loading…
Added a script to play Breakout with an acktr checkpoint.
#122 opened Aug 29, 2017 by Bleyddyn Loading…
1
Save, Load, & Visualize PPO results
#96 opened Aug 10, 2017 by ashwinreddy Loading…
4
Allow specifying different sizes of hidden layers.
#86 opened Aug 2, 2017 by hamzamerzic Contributor Loading…
ProTip! Adding no:label will show everything without a label.