Stable-Baselines-Team/stable-baselines3-contrib issues and pull requests

#276 - Use `has_attr` for detecting masking support, fixes several issues

Pull Request - State: closed - Opened by araffin 16 days ago

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

Pull Request - State: open - Opened by Soham4001A 19 days ago

#274 - Fix crash using SubprocVecEnv with MaskablePPO (#49)

Pull Request - State: closed - Opened by KiuIras 21 days ago - 1 comment

#273 - [Feature Request] Group Relative Proximity Optimization (GRPO)

Issue - State: open - Opened by Soham4001A 21 days ago - 2 comments
Labels: enhancement

#272 - GPRO - Feature Addition

Pull Request - State: open - Opened by Soham4001A 21 days ago

#271 - Release 2.5.0

Pull Request - State: closed - Opened by araffin 23 days ago

#270 - [Bug]: in "RecurrentPPO" not work "model.policy.evaluate_actions()"

Issue - State: open - Opened by drulye about 1 month ago - 2 comments
Labels: bug, more information needed, check the checklist

#269 - [Feature Request] Support for multi input policies in CrossQ

Issue - State: open - Opened by RaikoPipe about 1 month ago - 1 comment
Labels: enhancement

#268 - Added MultiInputPolicy support to CrossQ

Pull Request - State: open - Opened by RaikoPipe about 1 month ago

#267 - [Feature Request] ACERAC

Issue - State: open - Opened by lychanl 3 months ago - 2 comments
Labels: enhancement

#266 - Add policy documentation links to policy_kwargs parameter

Pull Request - State: closed - Opened by kplers 3 months ago

#265 - [Question] Not updating lstm states during training

Issue - State: open - Opened by abhinavj98 3 months ago - 1 comment
Labels: question

#264 - Add missing condition in CI

Pull Request - State: closed - Opened by araffin 3 months ago

#263 - Drop python 3.8, add python 3.12 support

Pull Request - State: closed - Opened by araffin 3 months ago

#262 - Release v2.4.0

Pull Request - State: closed - Opened by araffin 3 months ago

#261 - Add support for gymnasium v1.0

Pull Request - State: closed - Opened by araffin 4 months ago

#260 - Update deps for read the doc

Pull Request - State: closed - Opened by araffin 4 months ago

#259 - Fix QRDQN loading `target_update_interval`

Pull Request - State: closed - Opened by jak3122 5 months ago

#258 - [Bug]: loading QRDQN changes target_update_interval

Issue - State: closed - Opened by jak3122 5 months ago
Labels: bug

#257 - [Question] Why can't directly use the PPO (RecurrentActorCriticPolicy, "CartPole - v1", verbose = 1)

Issue - State: open - Opened by dajianer 6 months ago - 1 comment
Labels: question, more information needed, check the checklist

#256 - [Bug]: Is sb3_contrib/common/maskable/utils.py the cause of "WARN: env.action_masks to get variables from other wrappers is deprecated and will be removed in v1.0"?

Issue - State: open - Opened by mkbg8 6 months ago - 1 comment
Labels: enhancement, custom gym env

#255 - Fix warning when loading a `RecurrentPPO` model

Pull Request - State: closed - Opened by araffin 6 months ago

#254 - [Bug]: FutureWarning: You are using `torch.load` with `weights_only=False`

Issue - State: closed - Opened by drulye 6 months ago - 3 comments
Labels: bug, more information needed

#253 - [Feature Request] same random seed for every env in AsyncEval

Issue - State: open - Opened by 1-Bart-1 7 months ago - 1 comment
Labels: enhancement, check the checkboxes

#252 - Update QR-DQN optimizer to only use q_net parameters

Pull Request - State: closed - Opened by corentinlger 8 months ago - 1 comment

#251 - Update SB3 and remove gSDE resampling

Pull Request - State: closed - Opened by araffin 8 months ago

#250 - [Question] Masked actions PPO in multiagent setting using PettigZoo

Issue - State: open - Opened by MarcoPicione 8 months ago
Labels: question

#249 - [Question] Apply Masking using ActionMasker on composite actions

Issue - State: closed - Opened by mwalidcharrwi 8 months ago - 4 comments
Labels: duplicate, question, more information needed

#248 - [Question] How to do pre-training on the RecurrentPPO MlpLstmPolicy

Issue - State: open - Opened by iwishiwasaneagle 9 months ago - 1 comment
Labels: question

#247 - MaskablePPO Masking Doesn't Work with Big Action Space

Issue - State: closed - Opened by orkunkn 10 months ago - 4 comments
Labels: custom gym env, check the checklist

#246 - RecurrentActorCriticPolicy Behaviour Not Clear

Issue - State: open - Opened by pasinit 10 months ago - 1 comment
Labels: documentation

#245 - TQC: ep_len_mean and ep_rew_mean does not match real values

Issue - State: open - Opened by btabia 10 months ago
Labels: bug, custom gym env, check the checkboxes

#244 - ep_len_mean discrepancy

Issue - State: closed - Opened by btabia 10 months ago
Labels: custom gym env

#243 - Implemented CrossQ

Pull Request - State: closed - Opened by danielpalen 10 months ago - 11 comments

#242 - Dependent Actions in MultiDiscrete Action Space

Issue - State: open - Opened by bbarisbaturay 10 months ago - 5 comments
Labels: question

#241 - [Question] Recurrent Maskable PPO ?!? Rudder ?!?

Issue - State: closed - Opened by tty666 10 months ago - 1 comment
Labels: duplicate, question, trading warning

#240 - [Question] What is the difference between old_distribution and distribution in train function of TRPO

Issue - State: closed - Opened by 0Addicted0 10 months ago - 2 comments
Labels: question

#239 - [Question] RecurrentPPO: Reset LSTM states early?

Issue - State: open - Opened by phisad 11 months ago - 3 comments
Labels: enhancement, question

#238 - [Feature Request] Implement CrossQ

Issue - State: closed - Opened by danielpalen 11 months ago
Labels: enhancement

#237 - Fix typo in changelog

Pull Request - State: closed - Opened by araffin 11 months ago

#236 - Release v2.3.0

Pull Request - State: closed - Opened by araffin 11 months ago

#235 - Log success rate for PPO variants

Pull Request - State: closed - Opened by araffin 11 months ago

#234 - [Question] Why does MaskablePPO does not mask with some logic with last observation?

Issue - State: open - Opened by EloyAnguiano 11 months ago - 4 comments
Labels: question

#233 - Fix PPO maskable type annotations

Pull Request - State: closed - Opened by araffin 12 months ago

#232 - Update ruff and SB3 dependencies

Pull Request - State: closed - Opened by araffin 12 months ago

#231 - [Question] Simple way to implement data augmentation when training agent

Issue - State: closed - Opened by thomashirtz 12 months ago - 2 comments
Labels: question

#230 - [Question] LSTM observations

Issue - State: closed - Opened by suargi about 1 year ago - 3 comments
Labels: question

#229 - Fix `train_freq` type annotation for TQC and QR-DQN

Pull Request - State: closed - Opened by Armandpl about 1 year ago

#228 - Episodic training with TQC?

Issue - State: closed - Opened by Armandpl about 1 year ago - 2 comments
Labels: enhancement, question

#227 - Add note about MaskableEvalCallback

Pull Request - State: closed - Opened by icheered about 1 year ago

#226 - EvalCallback crashes Maskable PPO without error

Issue - State: closed - Opened by icheered about 1 year ago - 3 comments
Labels: documentation, help wanted, custom gym env

#225 - Update QRDQN defaults

Pull Request - State: closed - Opened by araffin about 1 year ago

#224 - Implementing "Sibling Rivalry" Method from "Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards" Paper

Issue - State: open - Opened by vladyskai about 1 year ago - 2 comments
Labels: enhancement

#223 - [Feature Request] STAC algorithm

Issue - State: open - Opened by EloyAnguiano about 1 year ago - 4 comments
Labels: enhancement

#222 - [Question] how to use "lstm_states" from rollout_buffer to reconstruct LSTM states during training

Issue - State: closed - Opened by DeepRowLie about 1 year ago - 2 comments
Labels: question

#221 - [Bug]: producing NAN values during training in MaskablePPO

Issue - State: open - Opened by vahidqo about 1 year ago - 5 comments
Labels: bug, more information needed, custom gym env, No tech support

#220 - [Feature Request] Expand RNN Options and Algorithm Flexibility

Issue - State: open - Opened by mtnusf97 about 1 year ago - 2 comments
Labels: enhancement

#219 - Update `_process_sequence()` docstring

Pull Request - State: closed - Opened by rogerioagjr about 1 year ago

#218 - [Question] Recurrent PPO evaluation

Issue - State: closed - Opened by CAI23sbP over 1 year ago - 2 comments
Labels: question

#217 - Release v2.2.1: hotfix file closing

Pull Request - State: closed - Opened by araffin over 1 year ago

#216 - Release v2.2.0

Pull Request - State: closed - Opened by araffin over 1 year ago

#215 - Remove PyType and upgrade to latest SB3 version

Pull Request - State: closed - Opened by araffin over 1 year ago

#214 - Add rollout_buffer_class to TRPO

Pull Request - State: closed - Opened by ernestum over 1 year ago - 2 comments

#213 - Sync SB3 Contrib with SB3

Pull Request - State: closed - Opened by araffin over 1 year ago

#212 - Predicting actions after using MaskablePPO model outputs invalid action

Issue - State: closed - Opened by vivek-kumar9696 over 1 year ago - 2 comments
Labels: duplicate, question, RTFM

#211 - Recurrent PPO Not Training Well on a Very Simple Environment

Issue - State: open - Opened by sreejank over 1 year ago - 1 comment
Labels: custom gym env, No tech support

#210 - Worse training with Vectorized Environment

Issue - State: closed - Opened by pklochowicz over 1 year ago
Labels: more information needed, custom gym env, No tech support

#209 - How to use LSTM ? RecurrentPPO from sb3-contrib

Issue - State: closed - Opened by PedroIAgithub over 1 year ago - 6 comments
Labels: question

#208 - Maskable PPO selects illegal actions, altough everything looks correct

Issue - State: closed - Opened by DominikRoB over 1 year ago - 2 comments
Labels: duplicate, question, more information needed

#207 - Decrease in reward during training with MaskablePPO

Issue - State: open - Opened by vahidqo over 1 year ago
Labels: question, more information needed, custom gym env

#206 - [Feature Request] BBF algorithm implementation

Issue - State: open - Opened by Alian3785 over 1 year ago - 2 comments
Labels: enhancement

#205 - Speed up when using MaskablePPO

Issue - State: open - Opened by vahidqo over 1 year ago - 2 comments
Labels: question

#204 - Release v2.1.0

Pull Request - State: closed - Opened by araffin over 1 year ago

#203 - SACD Discrete Soft Actor Critic

Pull Request - State: open - Opened by splatter96 over 1 year ago - 3 comments

#202 - [Feature Request] Hybrid PPO

Issue - State: open - Opened by AlexPasqua over 1 year ago - 3 comments
Labels: enhancement

#201 - [Feature Request] Implement Recurrent SAC

Issue - State: open - Opened by masterdezign over 1 year ago - 17 comments
Labels: enhancement

#200 - [Bug]: inappropriate actions despite the MaskablePPO applied

Issue - State: closed - Opened by koliber31 over 1 year ago - 1 comment
Labels: custom gym env, No tech support, check the checkboxes

#199 - Bugfix/ppo mask stats window size

Pull Request - State: closed - Opened by PatrickHelm over 1 year ago - 3 comments

#198 - [Bug]: MaskablePPO ignores stats_window_size argument

Issue - State: closed - Opened by PatrickHelm over 1 year ago - 2 comments
Labels: bug, help wanted

#197 - [Question] Action mask dimensions for action combinations in a MultiDiscrete space

Issue - State: closed - Opened by npit over 1 year ago - 2 comments
Labels: question

#196 - [Question] Example running error about PPO

Issue - State: closed - Opened by LoveingStatistics over 1 year ago - 3 comments
Labels: duplicate, question

#195 - Problems with MaskablePPO

Issue - State: open - Opened by koliber31 over 1 year ago - 16 comments
Labels: custom gym env

#194 - Drop python 3.7, add 3.11 and update github templates

Pull Request - State: closed - Opened by araffin over 1 year ago

#193 - [Question] Would you like a pull request implementing classical tabular RL algorithms ?

Issue - State: open - Opened by Butanium over 1 year ago - 1 comment
Labels: question

#192 - Release v2.0.0

Pull Request - State: closed - Opened by araffin over 1 year ago

#191 - [Question] What's the best way to store aditional data in transitions for an OffPolicyAlgorithm

Issue - State: closed - Opened by Butanium over 1 year ago - 6 comments
Labels: question

#190 - Update version and fix #188

Pull Request - State: closed - Opened by araffin over 1 year ago

#189 - [Question] macOS support tensorflow GPU, but sb3 installed with torch default? and output default"using cpu device"

Issue - State: closed - Opened by Pborz over 1 year ago - 2 comments
Labels: question

GitHub / Stable-Baselines-Team/stable-baselines3-contrib issues and pull requests