vwxyzjn/cleanrl

Issues

• PPO Complex Obs/Action Space

  #353 opened a year ago
  3

• About PPO+Procgen code on Jax

  #352 opened 6 months ago
  7

• Reproduction of Muesli

  #350 opened 6 months ago
  23

• Add Polyak update to DQN

  #346 opened a year ago
  1

• Deprecate `ppo_procgen.py` in favor of EnvPool

  #340 opened 6 months ago
  2

• What is the reason for returning mean in SAC get_action function if it's never used?

  #333 opened a year ago
  1

• Cleanrl for MARL

  #330 opened 6 months ago
  15

• GitPod instance errors out when running poetry install

  #325 opened 2 years ago
  3

• Typo in c51.py

  #324 opened 2 years ago
  1

• Target network isn't updated to the correct frequency when `target_network_frequency % train_frequency != 0`

  #322 opened 2 years ago
  0

• Benchmark `dqn_jax.py` using CPU only

  #317 opened a year ago
  0

• Why is there no design evaluation and save model module?

  #310 opened 2 years ago
  22

• DDPG JAX breaks with python ~3.7

  #309 opened 6 months ago
  2

• unable to render video in gitpod

  #305 opened 2 years ago
  0

• SAC Implementation Details

  #304 opened 2 years ago
  0

• cuda with SAC

  #303 opened 2 years ago
  1

• Action bias is added twice in DDPG algorithm implementation, similar to #259

  #297 opened 2 years ago
  0

• RLops Guide

  #296 opened a year ago
  1

• ppo+lstm train continuous environments

  #290 opened 2 years ago
  8

• Re-benchmarking refactored algorithms

  #289 opened 2 years ago
  1

• Requirments - requirements-pettingzoo.txt

  #283 opened 2 years ago
  3

• Problem with multi-agent atari

  #280 opened 2 years ago
  2

• TD3 policy noise bugs

  #279 opened 2 years ago
  2

• Are you interested in PRs for improvements in performance of PPO LSTM script?

  #276 opened 2 years ago
  3

• SAC discrete

  #266 opened 6 months ago
  3

• Multi-objective hyperparameter optimization

  #265 opened 2 years ago
  3

• Upgrade gym version to 0.26.1

  #263 opened 6 months ago
  2

• Action bias is added twice in TD3 algorithm implementation

  #259 opened 2 years ago
  2

• Add TQC to CleanRL

  #258 opened 2 years ago
  5

• Data corruption due to run naming convention when running on Slurm/GridEngine

  #256 opened 2 years ago
  1

• DQN on MountainCar

  #255 opened 2 years ago
  3

• Adding unit tests

  #252 opened 2 years ago
  0

• Poetry install fails with "isaacgymenvs (rev poetry) is not satisfied"

  #251 opened 2 years ago
  6

• Adding Double DQN

  #250 opened 2 years ago
  1

• RL Formulation

  #249 opened 2 years ago
  1

• Adding Hierarchical RL Algorithms

  #248 opened 6 months ago
  7

• Poetry can't install torch nightly

  #247 opened 2 years ago
  2

• Adding TRPO implementation

  #245 opened 6 months ago
  5

• AsyncVectorEnv

  #244 opened 2 years ago
  3

• A question about the `PPO` algorithm

  #240 opened 2 years ago
  5

• Replace cloud utilities w/ `torchx`

  #239 opened 6 months ago
  1

• Slow `poetry` dependency locking time, and resolution

  #237 opened 6 months ago
  0

• JAX + C51

  #221 opened a year ago
  0

• JAX + DQN

  #220 opened 2 years ago
  1

• JAX + TD3

  #219 opened 2 years ago
  1

• JAX Integration with CleanRL

  #218 opened 2 years ago
  0

• Prototype TD3 with JAX

  #216 opened 2 years ago
  1

• PPO with Humanoid

  #215 opened 2 years ago
  2

• Adding Average Reward PPO proposal

  #210 opened 6 months ago
  3

• Remove the value function clipping

  #208 opened 6 months ago
  0