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
Loading GPU trained RPPO on CPU
#159
norikazu99
opened
1 year ago
7
SIL
#158
qgallouedec
opened
1 year ago
8
TypeError: OnPolicyAlgorithm.__init__() got an unexpected keyword argument 'create_eval_env'
#157
aleksanderhan
closed
1 year ago
2
issue about RPPO
#156
tingtingLiuLiu
closed
1 year ago
1
issue about Recurrent ppo
#155
tingtingLiuLiu
closed
1 year ago
5
Possible issue with Maskable PPO
#154
emrul
opened
1 year ago
4
Custom Environment
#153
Zaibali9999
opened
1 year ago
6
Add Gymnasium support
#152
araffin
closed
1 year ago
0
timestamp to episode in documentation
#151
theSquaredError
opened
1 year ago
0
MaskablePPO docs
#150
AlexPasqua
closed
1 year ago
0
trying to mask actions for an environment with dict observation and multidiscrete action space
#149
zbenmo
opened
1 year ago
4
the trace is from a new failing test. In the test I'm trying to mask environment with a dict observation space and multidiscrete action space.
#148
zbenmo
closed
1 year ago
2
added a failing test
#147
zbenmo
closed
1 year ago
3
gSDE noise sampling with TQC can raise ValueError due to nan in `log_std`
#146
qgallouedec
opened
1 year ago
1
[Feature request] `check_env` could cause crashes with MaskablePPO
#145
AlexPasqua
closed
1 year ago
4
[Feature request] Support python 3.11
#144
wkoot
closed
1 year ago
2
Getting wrapper warning during training and then training does not work
#143
gowthamnatarajan
closed
1 year ago
1
Actions masks not applied when using callback
#142
gowthamnatarajan
closed
1 year ago
4
Maskable PPO: Specify masking actions
#141
gowthamnatarajan
closed
1 year ago
1
[Bug] Performance differences between normal and masked PPO
#140
tyler-ingebrand
closed
1 year ago
2
IQN
#139
qgallouedec
opened
1 year ago
4
duplicate
#138
eric000888
closed
1 year ago
0
Removed shared layers in mlp_extractor
#137
AlexPasqua
closed
1 year ago
0
ENH: RecurrentPPO, support sequence observation space
#136
younik
closed
1 year ago
1
[Feature request] Recurrent PPO for sequence observation space
#135
younik
closed
1 year ago
4
Release v1.7.0
#134
araffin
closed
1 year ago
0
Deprecation of shared layers in `mlp_extractor`
#133
AlexPasqua
closed
1 year ago
3
v1.6.2 doesn't contain the deprecations as documented
#132
derek-rocheleau
closed
1 year ago
2
Standardize the use of ``from gym import spaces``
#131
qgallouedec
closed
1 year ago
0
[Feature] Non-shared features extractor in on-policy algorithms
#130
AlexPasqua
closed
1 year ago
1
Add support for Python 3.10
#129
qgallouedec
closed
1 year ago
0
Construct tensors directly on GPUs
#128
qgallouedec
closed
1 year ago
1
DuelingDQN
#127
qgallouedec
opened
1 year ago
10
DuelingDQN
#126
qgallouedec
closed
1 year ago
1
Upgrade CI/github-actions
#125
qgallouedec
closed
1 year ago
0
Expose modules in `__init__.py` with `__all__` attribute
#124
ZikangXiong
closed
1 year ago
0
Fix `stable_baselines3/common/distributions.py` type hint
#123
qgallouedec
opened
1 year ago
0
Fix `sb3_contrib/ars/policies.py` type hint
#122
qgallouedec
closed
1 year ago
8
Fix `sb3_contrib/common/recurrent/type_aliases.py` type hint
#121
qgallouedec
closed
1 year ago
0
Fix `sb3_contrib/common/utils.py` type hint
#120
qgallouedec
closed
1 year ago
1
Mypy type checking
#119
qgallouedec
closed
1 year ago
3
RecurrentPPO: 9x speedup - whole sequence batching
#118
b-vm
opened
1 year ago
9
[QUESTION] lstm_states for value prediction and action evaluation
#117
dylanprins
closed
1 year ago
2
Fix `Self` return type
#116
qgallouedec
closed
1 year ago
0
[Feature request] Implement OT-TRPO
#115
antonioterpin
opened
1 year ago
3
How to visualize RecurrentPPO policy network architecture
#114
ashleychung830
closed
1 year ago
1
PPORecurrent mini batch size inconsistent
#113
b-vm
opened
1 year ago
18
Fix reshape LSTM states
#112
araffin
closed
1 year ago
0
Recurrent lstm state being reshaped incorrectly
#111
kolbytn
closed
1 year ago
4
Questions regarding BPTT (backpropagation through time)
#110
ibagur
closed
1 year ago
3
Previous
Next