DLR-RM stable-baselines3 issues

DLR-RM / stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

https://stable-baselines3.readthedocs.io

MIT License

8.33k stars 1.6k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[Question] Creating a vectorized environment for SB3

#1959 wilhem opened 9 hours ago
0
Issued when using HER in a custom environment

#1958 wilhem opened 12 hours ago
5
[Bug]: PPO using SDE device issue.

#1957 llewynS opened 2 days ago
1
[Bug]: EOFError after running for a while

#1956 xutong05 opened 3 days ago
0
[Bug]: ModuleNotFoundError: No module named 'gymnasium.wrappers.monitoring'

#1955 wilhem closed 3 days ago
3
proposed fix for RunningMeanStd overflow

#1954 spiglerg opened 4 days ago
0
[Bug]: RunningMeanStd overflowing

#1953 spiglerg opened 4 days ago
0
StopTrainingOnMaxEpisodes Assertion Error for 'dones' in locals

#1952 KevinHan1209 opened 6 days ago
0
Imcompatibility with gym env despite having stable_baselines3 version 2.x

#1951 KevinHan1209 closed 1 week ago
1
ValueError: You have passed a tuple to the predict() function instead of a Numpy array or a Dict. You are probably mixing Gym API with SB3 VecEnv API: `obs, info = env.reset()` (Gym) vs `obs = vec_env.reset()` (SB3 VecEnv).[Bug]: bug title

#1950 KevinHan1209 closed 1 week ago
0
[Question] multi processus observation collection

#1949 kenzlegouge closed 4 days ago
1
[Question] How can I log Q-values of DQN using custom callback from stable baselines 3 in Tensorboard?

#1948 gglsmm closed 1 week ago
4
Fix broken link

#1947 ikamensh closed 2 weeks ago
2
[Question] DQN optimizer parameters

#1946 rtkbv opened 3 weeks ago
2
[Question] How to use gsde in PPO

#1945 CAI23sbP closed 1 week ago
4
Avoiding obstacles

#1944 rowanhossamm closed 3 weeks ago
0
[Question] About log of policy_gradient_loss

#1943 d505 closed 2 weeks ago
6
Fix variance issue where ypred explains y as infinity

#1942 Zhanwei-Liu closed 3 weeks ago
4
[Question] How to set learning rate and scheduler for custom feature extractor?

#1941 edwardjjj closed 1 week ago
1
You must pass an environment when using `HerReplayBuffer`

#1940 izvvv closed 1 month ago
0
Set CallbackList children's parent correctly

#1939 will-maclean closed 3 weeks ago
0
[Question] Relationship between n_step, episode, and advantage in episodic tasks

#1938 d505 closed 1 month ago
4
Fix error when loading a model that has net_arch manually set to None

#1937 jak3122 closed 4 weeks ago
4
[Question] Optimization of memory usage

#1936 zichunxx closed 1 week ago
8
[Feature Request] Random Network Distillation with PPO (RND-PPO)

#1935 edofazza closed 1 week ago
1
What does the output of model.learn mean?

#1934 LeZhengThu closed 1 month ago
3
Remove unnecessary SDE resampling in PPO update

#1933 brn-dev closed 4 days ago
1
Setting up seed in Custom Gym environment

#1932 Chainesh closed 1 month ago
5
[Question] Running Multi-threaded PPO training independently with no interference

#1931 n-kish opened 1 month ago
3
[Question] SAC, a torch model becomes a bool somehow

#1930 JaimeParker closed 1 month ago
1
[Question] Why resample SDE noise matrices in PPO optimzation?

#1929 brn-dev closed 4 days ago
4
[Bug]: Manually setting net_arch=None causes crash when loading model

#1928 jak3122 closed 4 weeks ago
3
Fix various typos

#1926 cschindlbeck closed 1 month ago
1
[Question] Why torch model in c++ got totally different output from python

#1925 JaimeParker closed 1 month ago
4
[Question] LSTM and SAC - Am I understanding the docs correctly?

#1924 DJT777 closed 1 month ago
3
[Question] A error while using SAC and DDPG

#1923 minxuef closed 1 month ago
1
Avoid torch type-error under torch.compile

#1922 amjames closed 1 month ago
0
SubprocVecEnv Sets Out-of-Range Seeds for My Environments (ScenarioNet Enviroment)

#1921 chrisgao99 closed 1 month ago
8
[Feature Request] Allow users to define gradient steps as a fraction of rollout time-steps

#1920 janakact closed 1 week ago
4
[Question] How to access to rollout (logger) data in callback

#1919 JaimeParker closed 1 month ago
2
[Question] The error about DQN--ep_len_mean&ep_rew_mean output

#1918 AnnyOrange closed 1 month ago
1
[Question] Pong environment with A2C not learning with example code

#1917 Tanis1304 closed 1 month ago
1
SAC model not properly saved

#1916 PabloVD closed 1 month ago
5
ValueError: could not broadcast input array from shape (23,) into shape (27,)

#1915 n-kish closed 1 month ago
2
Handing mission space in Babyai env

#1914 Chainesh closed 2 months ago
6
Hotfix: revert loading with `weights_only=True`

#1913 araffin closed 2 months ago
0
[Bug]: evaluate_policy called multiple times vor vectorized environments

#1912 LukasFehring opened 2 months ago
5
[Bug]: Load Trained Policy

#1911 zlw21gxy closed 2 months ago
8
Fix tensorboad video slow numpy->torch conversion

#1910 NickLucche closed 2 months ago
0
Discrepancy between Observations Sampled from Gym Env and Replay Buffer

#1909 AOAA96 closed 2 months ago
3