Pinned Loading

1. tinkoff-ai/CORL tinkoff-ai/CORL Public archive

   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 1.1k 135

2. tinkoff-ai/ReBRAC tinkoff-ai/ReBRAC Public archive

   Author's implementation of ReBRAC, a minimalist improvement upon TD3 BC

   Jupyter Notebook 54 6

3. ClORL ClORL Public

   Authors' implementation of the "Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?"

   Python 7

4. multi-agent-emergence-unity multi-agent-emergence-unity Public

   Reproduction of environment from paper "Emergent Tool Use From Multi-Agent Autocurricula" with Unity and ML-Agents

   C# 7 1