Pull requests: Stable-Baselines-Team/stable-baselines3-contrib

22 Open 131 Closed

Author

Filter by author

Loading

author:

Filter by this user

Label

Filter by label

Loading

Projects

Filter by project

Loading

Milestones

Filter by milestone

Loading

Reviews

Filter by reviews

No reviewsReview requiredApproved reviewChanges requested

Assignee

Filter by who’s assigned

Assigned to nobodyLoading

assignee:

Filter by this user

Sort

Sort by

NewestOldestMost commentedLeast commentedRecently updatedLeast recently updatedBest match

Most reactions

👍👎😄🎉😕❤️🚀👀

Pull requests list

Fix n_updates counting with early stopping in MaskablePPO and RecurrentPPO

#313 openedNov 16, 2025 byalektebelLoading…

4 tasks done

Add tests for PR #302 numerical stability fix (issue #81)

#311 openedNov 6, 2025 byCopilotAI • Draft

6 of 15 tasks

Fix Numerical issues in MaskPPO Training

#302 openedJul 20, 2025 bySarthak-DayalLoading…

8 of 15 tasks

1

Hybrid PPO

#300 openedJul 6, 2025 byAlexPasqua • Draft

3 of 15 tasks

1

4

Add vanilla RNN support toRecurrentPPO

#296 openedJun 11, 2025 bygcroci2Loading…

11 of 15 tasks

1

FixRecurrentRolloutBuffer not takingenv_change into account for resetting states

#290 openedMar 31, 2025 byaraffin • Draft

15 tasks

1

Maskable Recurrent PPO

#287 openedMar 23, 2025 byakbaigLoading…

4 of 15 tasks

1

4

Add unit tests for RecurrentDictRolloutBuffer

#286 openedMar 13, 2025 byDanielAvdar • Draft

15 tasks

Hybrid Group Relative Policy Optimization (Hybrid GRPO): A Multi-Sample Approach to Reinforcement Learning

#275 openedFeb 1, 2025 bySoham4001ALoading…

6 tasks

2

GPRO - Feature Addition

#272 openedJan 29, 2025 bySoham4001ALoading…

4 tasks

4

Added MultiInputPolicy support to CrossQ

#268 openedJan 8, 2025 byRaikoPipe • Draft

4 of 15 tasks

SACD Discrete Soft Actor Critic Maintainers on vacationMaintainers are on vacation so they can recharge their batteries, we will be back soon ;)

#203 openedAug 7, 2023 bysplatter96Loading…

11 of 16 tasks

7

PPO attention net (GTrXLNet)

#176 openedApr 11, 2023 byRemiG3 • Draft

3 of 15 tasks

1

4

Rename the observations variable in the evaluation util to avoid shadowing

#174 openedApr 9, 2023 bynpitLoading…

7 of 15 tasks

1

timestamp to episode in documentation

#151 openedFeb 11, 2023 bytheSquaredErrorLoading…

2 of 15 tasks

IQN

#139 openedJan 26, 2023 byqgallouedec • Draft

3 of 15 tasks

4

DuelingDQN

#127 openedDec 10, 2022 byqgallouedec • Draft

21 tasks

13

Fixstable_baselines3/common/distributions.py type hint

#123 openedNov 29, 2022 byqgallouedec • Draft

15 tasks

RecurrentPPO: 9x speedup - whole sequence batching

#118 openedNov 28, 2022 byb-vm • Draft

5 of 15 tasks

9

Feat/dropq

#100 openedAug 29, 2022 byaraffin • Draft

15 tasks

Noisy Cross Entropy Method (CEM)

#62 openedMar 6, 2022 byaraffinLoading…

15 tasks

1

Add the Bootstrapped Dual Policy Iteration algorithm for discrete action spaces

#35 openedJul 2, 2021 bysteckdenisLoading…

13 of 17 tasks

7