Google Research

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Implementation of Statistical Learning Method, Second Edition.《统计学习方法》第二版，算法实现。

Code for fintune ChatGLM-6b using low-rank adaptation (LoRA)

JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

neural networks to learn Koopman eigenfunctions

DayDreamer: World Models for Physical Robot Learning

KwaiRec: A Fully-observed Dataset for Recommender Systems.

Goal-Conditioned Reinforcement Learning with JAX

An AI for 3-player Mahjong (Sanma) using deep reinforcement learning