Skip to content

Pull requests: vwxyzjn/cleanrl

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Sort

Pull requests list

Add TD3 and SAC support for multiple envs
#481 opened Aug 27, 2024 by noahfarr Loading…
3 of 18 tasks
Add tomli, msgpack, cffi, pip as dependencies - Fixes #455
#479 opened Aug 17, 2024 by JuliusBairaktaris Loading…
3 of 18 tasks
Add Parallel Q-Networks algorithm (PQN)
#472 opened Jul 17, 2024 by roger-creus Loading…
4 of 18 tasks
Adding Munchausen Reinforcement Learning
#466 opened Jun 30, 2024 by Paul-antoineLeTolguenec Loading…
6 of 18 tasks
Add PPO + Transformer-XL
#459 opened Apr 22, 2024 by MarcoMeter Loading…
15 tasks done
Change actor_update_interval to policy_frequency in SAC comment
#458 opened Apr 22, 2024 by JinayJain Loading…
1 of 18 tasks
add accelerate example
#446 opened Feb 10, 2024 by edbeeching Draft
1 of 18 tasks
Adding TRPO
#435 opened Nov 30, 2023 by Jackory Loading…
3 of 18 tasks
feat: add vloss clipping to jax ppo.
#426 opened Oct 27, 2023 by KaleabTessera Loading…
3 of 18 tasks
Update ppo_pettingzoo_ma_atari.py
#408 opened Jul 12, 2023 by elliottower Loading…
1 of 18 tasks
handle num_envs > 1 in DQN
#395 opened Jun 6, 2023 by ronuchit Loading…
9 tasks
Adding MPO and DMPO
#392 opened May 23, 2023 by Jogima-cyber Loading…
6 of 18 tasks
add complex observation atari ppo
#359 opened Feb 15, 2023 by ttumiel Loading…
3 of 20 tasks
add tianshou-like JAX+PPO+Mujoco
#355 opened Jan 31, 2023 by quangr Draft
3 of 19 tasks
Parallel-envs-friendly ppo_continuous_action.py
#348 opened Jan 13, 2023 by vwxyzjn Draft
1 of 20 tasks
Brax + PPO integration
#313 opened Nov 6, 2022 by vwxyzjn Draft
1 of 20 tasks
SAC jax
#300 opened Oct 23, 2022 by araffin Loading…
6 of 20 tasks
Type hints
#293 opened Oct 14, 2022 by timoklein Draft
4 of 9 tasks
Algorithm: Option Critic methods
#278 opened Sep 27, 2022 by DavidSlayback Draft
2 of 17 tasks
Draft: DroQ and TD3+TQC jax implementation
#272 opened Sep 16, 2022 by araffin Draft
1 of 20 tasks
Implement PPO-DNA algorithm for Atari
#234 opened Jul 19, 2022 by jseppanen Loading…
11 of 21 tasks
ProTip! Adding no:label will show everything without a label.