🎯
Focusing
-
PURE Public
Forked from CJReinforce/PUREOfficial code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"
-
-
pylift Public
Forked from rsyi/pyliftUplift modeling and evaluation library. Actively maintained pypi version.
Python BSD 2-Clause "Simplified" License UpdatedDec 28, 2023 -
decision-transformer Public
Forked from kzl/decision-transformerOfficial codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.
Python MIT License UpdatedMay 27, 2023 -
VIMABench Public
Forked from vimalabs/VIMABenchOfficial Task Suite Implementation of Paper "VIMA: General Robot Manipulation with Multimodal Prompts"
Python MIT License UpdatedApr 25, 2023 -
-