Beast code in Giters

corl-team's repositories

CORL

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

Language:PythonApache-2.0408 3 10

xland-minigrid

JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️

Language:PythonApache-2.0153 7 12

rebased

Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"

Language:PythonApache-2.0136 5 4

katakomba

Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)

Language:PythonNOASSERTION3500

headless-ad

Official Implementation for "In-Context Reinforcement Learning for Variable Action Spaces"

Language:Python20 40

ad-eps

Official Implementation for "In-Context Reinforcement Learning from Noise Distillation"

Language:Python18 20

toy-meta-gym

Toy meta-RL environments for testing algorithms implementations

Language:PythonApache-2.04 30