Search Results - RepositoryStats

131

1.1k

apache-2.0

16

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

gym d4rl reinforcement-learning offline-reinforcement-learning

This repository has been archived (exclude archived)

Created 2022-09-23

44 commits to main branch, last one about a year ago

Gymnasium-Robotics Farama-Foundation

88

558

mit

12

A collection of robotics simulation environments for reinforcement learning

d4rl mujoco robotics gymnasium simulation reinforcement-learning

Created 2021-10-25

436 commits to main branch, last one 7 days ago

JAX-CORL nissymori

2

93

mit

4

Clean single-file implementation of offline RL algorithms in JAX

cql iql jax awac d4rl flax td3bc offline-rl single-file decision-transformer reinforcement-learning offline-reinforcement-learning

Created 2024-01-22

333 commits to main branch, last one 2 months ago

sac-n-jax Howuhh

3

46

mit

1

Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch

jax d4rl flax equinox reinforcement-learning offline-reinforcement-learning

Created 2022-11-28

13 commits to main branch, last one about a year ago

SRPO thu-ml

1

36

mit

6

Codes accompanying the paper "Score Regularized Policy Optimization through Diffusion Behavior" (ICLR 2024).

rl d4rl srpo offline diffusion generative score-based-models reinforcement-learning behavior-regularization

Created 2023-10-11

14 commits to main branch, last one 9 months ago