Applying AlphaZero Self-Play Tactics to LLaMA for Enhanced Chatbot Interaction

Simple Muesli RL algorithm implementation (PyTorch)

A set of experiments and human-playing comparisons with the Muzero agent from Google DeepMind, made as part of a research project with l'école polytechnique.

GenesisZERO : potential applications for MCTS agents with LLMs for Sequential decision-making

muzero Algorithm Reinforcement Learning for Chinese XiangQi

Meta-learning experiments for the game of minichess and related rule variants.

MuZero - tic-tac-toe

Learning how muzero works

Trains a deep reinforcement learning agent in simulation testbed environments with the DRLA library.

Trains deep reinforcement learning agents in Atari environments via the DRLA library.

MuZero for Super Mario Bros

A Notebook implementation of the Pseudocode from the original Muzero paper

Deep Q Learning blackbox strategies for casino games

Materials for AlphaGo

A robust variant of MuZero

AlphaZero for singleplayer environments implemented efficiently using Ray

C++ Deep Reinforcement Learning Agent library