DLR-RM/rl-baselines3-zoo

Issues

• [Question] RL traning could not reach convergence for a customised environment

  #449 opened a month ago by SKYLEO98
  0

• [Question] Number of parallel environments with hyperparameters optimization

  #446 opened a month ago by suargi
  1

• [Bug]: Training suddenly stops at 25000 timesteps and Optuna optimization immediately exits in my custom environment

  #441 opened a month ago by Silver812
  7

• [Bug]: Optimization log and optimal policy not in `--optimization-log-path` but in `--log-folder`

  #444 opened 2 months ago by turbotimon
  1

• [Bug]: Custom environment not found in gym registry, you maybe meant... error message

  #443 opened 2 months ago by jiceline03
  1

• [Question] exp_manager reward and GAE discount factors

  #442 opened 2 months ago by edmund735
  1

• [Question] Does hyperparameter tuning support custom vectorized environments?

  #439 opened 3 months ago by antoinedang
  6

• [Bug]: TODO: add test dependencies in the `setup.py`

  #435 opened 4 months ago by power-edge
  1

• [Bug]: video recording on Pybullet

  #412 opened 4 months ago by guillaumepourcel
  4

• [Question] Custom Eval Callback for train/optimize

  #434 opened 5 months ago by kingjin94
  2

• [Question] RuntimeError: Unable to sample before the end of the first episode. We recommend choosing a value for learning_starts that is greater than the maximum number of timesteps in the environment.

  #433 opened 5 months ago by moneypi
  5

• [Question] You must pass an environment when using `HerReplayBuffer`

  #432 opened 5 months ago by moneypi
  1

• [Bug]: Custom Sub-Hyperparameters during train.py -> Optimize

  #431 opened 6 months ago by kingjin94
  1

• Training DonkeyCar with TQC algorithm with pretrained AE

  #429 opened 6 months ago by jgamette
  0

• [Error]: I got unexpected error using enjoy() with pretrain model

  #428 opened 6 months ago by tiencapham
  4

• [Question] trying to run panda environments with RL zoo

  #392 opened 6 months ago by kiankyars
  2

• [Bug]: Nan Problems for SAC, TQC, for AntBulletEnv-v0, HalfCheetahBulletEnv-v0

  #427 opened 6 months ago by ZJEast
  9

• [Feature Request] Store git hash of key repos/packages

  #426 opened 7 months ago by araffin
  0

• [Bug]: Cannot enjoy due to error Cannot convert space of type Discrete(7). Please upgrade your code to gymnasium.

  #425 opened 7 months ago by notshashwat
  1

• [Feature Request] Call train from Python code

  #423 opened 7 months ago by younik
  2

• Issue with 'feat/offline-RL' Branch for Donkey Car in rl-baselines3-zoo

  #419 opened 7 months ago by Gribesh
  4

• [Question] Training Donkey Car Without Simulator Rendering

  #417 opened 7 months ago by Gribesh
  2

• [Bug]: ppo_lstm not implemented in hyperparams_opt.py

  #409 opened 7 months ago by technocrat13
  3

• Plotting Script Improvement

  #413 opened 8 months ago by VinayHajare
  1

• [Question] Support for Customized BaseFeaturesExtractor

  #411 opened 8 months ago by kingjin94
  1

• [Question] rl_zoo3 optimization pipeline for ros-based custom env

  #410 opened 8 months ago by ammar-n-abbas
  2

• [Bug]: enjoy panda policy in hugging face

  #408 opened 8 months ago by zhixiongzh
  7

• Error when using recommended plotting commands

  #387 opened a year ago by ikamensh
  3

• [Feature Request] Specify custom keyword arguments for eval environments

  #404 opened 9 months ago by Quentin18
  2

• [Feature Request] Remove gym dependency

  #398 opened 9 months ago by ernestum
  3

• [Bug]: Kwargs in `record_video.py` not preserved by SB3 Vector Environment wrappers

  #399 opened 9 months ago by anayebi
  4

• `optuna.trial.Trial.suggest_uniform()` deprecated

  #401 opened 9 months ago by alperenunlu
  0

• #enhancment

  #400 opened 9 months ago by alperenunlu
  0

• [Feature Request] Outdated dockerfile

  #391 opened 9 months ago by VineetTambe
  2

• [Feature Request] Add the `--gym-packages` flag to `record_video`

  #396 opened 9 months ago by Quentin18
  1

• [Question] exported ONNX model does not result in same output as the original pytorch model

  #394 opened 10 months ago by VineetTambe
  5

• Half-Cheetah reward function

  #393 opened 10 months ago by scakki
  0

• Upgrade all MuJoco envs to v4

  #385 opened a year ago by araffin
  3

• [Enhancement] Deprecate --gym-packages argument

  #390 opened a year ago by ernestum
  5

• [Question] Should "continue training" load the vecnormalize.pkl as well as the model.zip?

  #386 opened a year ago by xibeisiber
  2

• [Question] Correct way of hyper parameter optimization for new algorithm?

  #384 opened a year ago by tyler-ingebrand
  1

• Add link to custom environments page in sb3 docs

  #383 opened a year ago by Melanol
  0

• [Question] No module named 'ae' when running train.py

  #377 opened a year ago by Guosy0506
  1

• [Bug]: enjoy tries to access huggingface

  #382 opened a year ago by Melanol
  4

• [Bug]: TypeError: 'EnvRegistry' object is not iterable

  #381 opened a year ago by Melanol
  5

• [Question] Unnecessary Hyperparameter Values for DQN Cartpole-v1

  #380 opened a year ago by prabhatnagarajan
  0

• [Question] The performance for Hopper-v3 doesn't get converged for PPO

  #376 opened a year ago by cx441000319
  5

• [Question] full_action_space not working as expected

  #375 opened a year ago by Bleyddyn
  4

• [Question] Plotting Smoothed Evaluation Curve

  #371 opened a year ago by Zachary-Fernandes
  1

• error due to model and env observation space mismatch when I load pretrained agent

  #369 opened a year ago by chang2727
  3