All pull requests

Pull requests

• Add experimental Nebius Serverless Jobs example

  #575·SalikovAlex opened Sep 12, 2026·8 of 11 tasks·

  ·
  1

• docs: correct TensorBoard working directory

  #570·quinnarnold opened Aug 22, 2026·5 of 11 tasks·

  ·
  1

  1

• Fix enjoy.py crash: re-add missing --capture_video argument

  #561·YangNuoCheng opened Jun 24, 2026·3 of 6 tasks·

  ·
  1

  1

• Add unit tests for ppo_continuous_action GAE computation

  #560·YangNuoCheng opened Jun 24, 2026·4 of 7 tasks·

  ·
  1

• Add unit tests for PPO GAE computation

  #559·YangNuoCheng opened Jun 24, 2026·4 of 7 tasks·

  ·
  1

• ci: add dedicated ruff lint workflow

  #558·dashitongzhi opened Jun 14, 2026·1 of 3 tasks·

  ·
  6

• Fix Rainbow segment tree sampling for non-power-of-two capacities

  #557·discobot opened Jun 13, 2026·4 of 18 tasks·

  ·
  1

  1

• Fix: reuse training obs normalization stats in ppo_continuous_action eval

  #556·discobot opened Jun 13, 2026·4 of 18 tasks·

  ·
  1

  1

• perf: avoid tensor memory copy in ppo_atari_envpool, pqn_atari_envpool, ppo_rnd_envpool, and ppo_procgen

  #552·srygaard opened May 4, 2026·5 of 19 tasks·

  ·
  1

• fix(enjoy): restore --capture-video argument removed in #424

  #550·mturan33 opened Apr 20, 2026Contributor·4 tasks done·

  ·
  1

  1

• Security: Command injection via unsanitized Docker tag in shell command

  #548·tuanaiseo opened Apr 15, 2026·3 tasks·

  ·
  1

• fix: update JAX dependency stack to modern compatible versions

  #544·Okyumi opened Mar 19, 2026·

  ·
  1

  1

• Fix #508: Use per-env logging_step for episodic return logging

  #539·kumar-pankaj0 opened Mar 2, 2026·

  ·
  1

  3

• Fixes Issue #533 - Fix tuner dropping the first CLI argument.

  #536·hliu-ai opened Jan 12, 2026·3 of 18 tasks·

  ·
  1

  2

• Refactor: Enforce explicit reshape and consistent 2D output in swap_and_flatten

  #535·ZHYsfl opened Jan 2, 2026·3 of 8 tasks·

  ·
  1

• Add ES-C51 (Expected Sarsa based C51)

  #529·Rijul-Tandon opened Oct 9, 2025·5 of 18 tasks·

  ·
  19

• [Enhancement] Log mean/max KL across PPO update phase

  #523·pjain03 opened Aug 27, 2025·8 of 18 tasks·

  ·
  1

• Add SAC Jax Implementation (reloaded)

  #519·araffin opened Jul 17, 2025·1 of 18 tasks·

  ·
  1

• Update to Gymnasium v1.0

  #516·pseudo-rnd-thoughts opened Jul 5, 2025Collaborator·4 of 18 tasks·

  ·
  2

• feat: port isaacgym example to isaaclab

  #513·lvjonok opened Jun 17, 2025·3 of 18 tasks·

  ·
  1

• [Non-performance-impacting update] Use Pytorch DDP in ppo_atari_multigpu

  #495·realAsma opened Jan 14, 2025·4 of 18 tasks·

  ·
  4

• Adding Munchausen Reinforcement Learning

  #466·Paul-antoineLeTolguenec opened Jun 30, 2024·6 of 18 tasks·

  ·
  1

• Change actor_update_interval to policy_frequency in SAC comment

  #458·JinayJain opened Apr 22, 2024·1 of 18 tasks·

  ·
  1

• Enhancing Termination and Truncation Handling in CleanRL's PPO Algorithm

  #448·Josh00-Lu opened Feb 29, 2024·6 of 20 tasks·

  ·
  10

• add accelerate example

  #446·edbeeching opened Feb 10, 2024·1 of 18 tasks·

  ·
  17