Skip to content

Pull requests: chainer/chainerrl

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

FQF (Fully Parameterized Quantile Function) agent
#579 opened Nov 10, 2019 by muupan Member Draft
1 task
Support 'spawn' in async training
#574 opened Nov 7, 2019 by muupan Member Draft
[WIP] Use chainer.as_variable enhancement
#510 opened Jul 18, 2019 by muupan Member Loading…
[WIP] IMPALA-style actor-learner parallelism for DQN variants
#477 opened Jun 11, 2019 by muupan Member Loading…
[WIP] Support chainer.distributions in TRPO
#454 opened May 6, 2019 by muupan Member Loading…
[WIP] ChainerX support by DQN
#375 opened Dec 28, 2018 by muupan Member Loading…
2 tasks
[WIP] Implements Hindsight Experience Replay
#361 opened Nov 26, 2018 by prabhatnagarajan Contributor Loading…
add act_with_exploration() method
#298 opened Aug 17, 2018 by LorenzoM1997 Loading…
Rewrite PCL agent
#245 opened Feb 25, 2018 by lyx-x Contributor Loading…
[WIP] Avoid action_space.sample
#244 opened Feb 15, 2018 by muupan Member Loading…
Fix the usage of t_max in PCL
#237 opened Feb 14, 2018 by lyx-x Contributor Loading…
[WIP] Enable appending arbitrary values to replay buffer
#224 opened Jan 29, 2018 by muupan Member Loading…
[WIP] Save and load lists
#223 opened Jan 29, 2018 by muupan Member Loading…
ProTip! Updated in the last three days: updated:>2026-04-18.