YeWR/EfficientZero

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

This repository contains implementations and illustrative code to accompany DeepMind publications

Mastering Diverse Domains through World Models

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Readable single-file PyTorch implementations of deep RL algorithms: DQN, PPO, SAC, TD3, DDPG and A2C, with Gymnasium and Atari support plus W&B tracking.

A library of reinforcement learning components and agents

📄Score Centering Stabilizes Off-policy Reinforcement Learning

Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind

[IEEE ToG] MiniZero: An AlphaZero and MuZero Training Framework