Pinned

1. CORL CORL Public

   Forked from tinkoff-ai/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

   Python 402 15

2. xland-minigrid xland-minigrid Public

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

   Python 148 10

3. rebased rebased Public

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

   Python 133 4

4. katakomba katakomba Public

   Forked from tinkoff-ai/katakomba

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

   Python 35 2

5. ad-eps ad-eps Public

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

   Python 17

6. headless-ad headless-ad Public

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

   Python 18