issues
search
Stable-Baselines-Team
/
stable-baselines3-contrib
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
https://sb3-contrib.readthedocs.io
MIT License
465
stars
173
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to use LSTM ? RecurrentPPO from sb3-contrib
#209
PedroIAgithub
closed
1 year ago
6
Maskable PPO selects illegal actions, altough everything looks correct
#208
DominikRoB
closed
1 year ago
2
Decrease in reward during training with MaskablePPO
#207
vahidqo
opened
1 year ago
0
[Feature Request] BBF algorithm implementation
#206
Alian3785
opened
1 year ago
2
Speed up when using MaskablePPO
#205
vahidqo
opened
1 year ago
2
Release v2.1.0
#204
araffin
closed
1 year ago
0
SACD Discrete Soft Actor Critic
#203
splatter96
opened
1 year ago
3
[Feature Request] Hybrid PPO
#202
AlexPasqua
opened
1 year ago
0
[Feature Request] Implement Recurrent SAC
#201
masterdezign
opened
1 year ago
17
[Bug]: inappropriate actions despite the MaskablePPO applied
#200
koliber31
closed
1 year ago
1
Bugfix/ppo mask stats window size
#199
PatrickHelm
closed
1 year ago
3
[Bug]: MaskablePPO ignores stats_window_size argument
#198
PatrickHelm
closed
1 year ago
2
[Question] Action mask dimensions for action combinations in a MultiDiscrete space
#197
npit
closed
1 year ago
2
[Question] Example running error about PPO
#196
LoveingStatistics
closed
1 year ago
3
Problems with MaskablePPO
#195
koliber31
opened
1 year ago
16
Drop python 3.7, add 3.11 and update github templates
#194
araffin
closed
1 year ago
0
[Question] Would you like a pull request implementing classical tabular RL algorithms ?
#193
Butanium
opened
1 year ago
1
Release v2.0.0
#192
araffin
closed
1 year ago
0
[Question] What's the best way to store aditional data in transitions for an OffPolicyAlgorithm
#191
Butanium
closed
1 year ago
6
Update version and fix #188
#190
araffin
closed
1 year ago
0
[Question] macOS support tensorflow GPU, but sb3 installed with torch default? and output default"using cpu device"
#189
Pborz
closed
1 year ago
2
Note for later: update build script
#188
araffin
closed
1 year ago
0
[Question] what would I got if I manage the train like this in SubprocVecEnv?
#187
Pborz
closed
1 year ago
5
Timestamp as observation
#186
AminDar
closed
1 year ago
2
Update AsyncEval seeding
#185
araffin
closed
1 year ago
0
seems that python3.10 not include all sb3_contrib yet
#184
Pborz
closed
1 year ago
2
Architecture of PPO LSTM
#183
anilkurkcu
closed
1 year ago
5
Update doc: switch from Gym to Gymnasium
#182
araffin
closed
1 year ago
0
Issue with PIP
#181
anilkurkcu
closed
1 year ago
1
[Feature Request] Domain Randomization
#180
KonstantinRamthun
opened
1 year ago
2
Recurrent PPO
#179
fede72bari
closed
1 month ago
4
[Feature Request] Maskable EvalCallback support
#178
DnzJS
closed
1 year ago
2
How to use maskable PPO
#177
anilkurkcu
closed
1 year ago
1
PPO attention net (GTrXLNet)
#176
RemiG3
opened
1 year ago
2
[Question] Rewriting the Stable Baseline Docs with MkDocs with good UI and UX
#175
Siddhu2502
opened
1 year ago
4
Rename the observations variable in the evaluation util to avoid shadowing
#174
npit
opened
1 year ago
1
Release v1.8.0
#173
araffin
closed
1 year ago
0
[Question] Setting net_arch of recurrent policies
#172
joelmichelson
closed
1 year ago
2
Add stats window argument
#171
jonasreiher
closed
1 year ago
1
Fix QR-DQN type hints
#170
araffin
closed
1 year ago
0
[Question During training of a RecurrentPPO agent, does the "lstm_states" reset at the end of each episode?
#169
HaakonFlaaronning
closed
1 year ago
1
[Question] What modifications do I need to mask the inputs similar to how MaskablePPO masks the outputs?
#168
rllyryan
opened
1 year ago
0
Update SB3 and config
#167
araffin
closed
1 year ago
0
MaskablePPO does not remove invalid mask action
#166
AbelSyx
closed
1 year ago
2
[Feature Request] Add Attention nets (GTrXL model in particular)
#165
RemiG3
opened
1 year ago
13
Fix Atari Roms Download
#164
araffin
closed
1 year ago
0
Create custom recurrent policy
#163
kundan-kumarr
closed
1 year ago
2
Issue forms and pyproject.toml
#162
araffin
closed
1 year ago
0
MaskablePPO doesn't set _num_timesteps_at_start so fps count is wrong when reset_num_timesteps=False in learn()
#161
Naton1
opened
1 year ago
1
How to get activations for layers?
#160
ashleychung830
closed
1 year ago
6
Previous
Next