Pinned issues
Issues
- 4
Contributing PPO + Transformer-XL
#442 opened by MarcoMeter - 1
Unable to allocate 26.3 GiB for an array
#453 opened by satyrmipt - 0
KeyError: 'cleanba_ppo_envpool_procgen'
#452 opened by zhixiongzh - 0
Docker image is out of date
#451 opened by myxik - 0
- 2
Potential bug in PPO+RND?
#416 opened by roger-creus - 1
- 1
- 0
clamp in C51
#443 opened by XinJingHao - 0
Reproduction util: wrong command path
#440 opened by qgallouedec - 3
Fail to record video
#384 opened by yxdydgithub - 2
Why converting observation space to np.float32?
#438 opened by jamartinh - 2
- 5
Poor Evaluation Performance in PPO
#425 opened by sdpkjc - 8
- 4
Liberate the requirements.txt
#387 opened by ThijsvandenBerg - 4
Video upload Issue - wandb
#397 opened by tbasaklar - 7
About PPO+Procgen code on Jax
#352 opened by sglucas - 23
Reproduction of Muesli
#350 opened by vwxyzjn - 1
numpy version issue with python 3.10
#417 opened by martin-nginio - 10
Pyyaml error on poetry install
#418 opened by hom-bahrani - 2
[BUG] Env does not reset when it's terminated
#432 opened by modanesh - 4
expected sequence of length 8 at dim 1 (got 0)
#431 opened by flypark666 - 0
[BUG] Different final epsilon and evaluation epsilon for Atari implementations
#429 opened by pseudo-rnd-thoughts - 2
get action in sac_continuous_action.py
#428 opened by zichunxx - 4
- 5
- 2
Performance compared with SB3
#405 opened by qiuruiyu - 3
How to do evaluation for example on PPO
#400 opened by qiuruiyu - 5
Bug in actor loss for sac_continuous_action.py
#379 opened by terencenwz - 3
SAC cannot converge to optimal policy
#410 opened by mahaozhe - 0
Adding new dependencies for ManiSkill2 clean rl
#413 opened by StoneT2000 - 1
Clean Offline RL (CORL) moved to a new fork
#411 opened by vkurenkov - 4
Poetry installation failure on master
#391 opened by smorad - 2
Is action masking supported in PPO?
#402 opened by aqibsaeed - 6
The GAE calculation in PPO continuous action
#393 opened by baixianger - 4
Are you interested in adding MPO
#390 opened by Jogima-cyber - 0
Duplicate code in README.md
#388 opened by helpingstar - 3
Bug of cleanrl_utils/evals
#380 opened by sdpkjc - 2
- 0
Buy the contributors a cup of coffee
#374 opened by ShuoZheLi - 0
- 1
- 2
- 4
code error when running dqn.py
#364 opened by jianzuo - 1
Is SAC exploration-noise used?
#361 opened by StoneT2000 - 1
Bug in RND Intrinsic Reward Normalization
#360 opened by akarshkumar0101 - 0
- 2
The file 'ppo_memory_env_lstm.py' can't be found
#356 opened by leeivan1007 - 3
PPO Complex Obs/Action Space
#353 opened by ttumiel