RLG Lab

All

11 repositories

minizero
Public
[IEEE ToG] MiniZero: An AlphaZero and MuZero Training Framework
go hex reinforcement-learning
go hex reinforcement-learning deep-reinforcement-learning mcts othello gomoku tictactoe atari monte-carlo-tree-search
C++
•36•124•3•0•Updated Feb 25, 2026Feb 25, 2026
study-LD-RZ
Public
[IEEE ToG] A Study of Solving Life-and-Death Problems in Go Using Relevance-Zone Based Solvers
go mcts heuristic-search
go mcts heuristic-search alphazero mote-carlo-tree-search life-and-death-problems relevance-zone
C
•0•0•0•0•Updated Feb 4, 2026Feb 4, 2026
maq
Public
[NeurIPS 2025] A human-like RL framework that improves human-likeness while achieving strong performance, and can be easily integrated into various RL algorithm…
reinforcement-learning robotics trajectory-optimization
reinforcement-learning robotics trajectory-optimization adroit human-like d4rl
Python
•0•1•0•0•Updated Jan 27, 2026Jan 27, 2026
neurips2025-mind-games-efficient-agent-social-deduction-track-rlgaming
Public
Python
•0•1•0•0•Updated Nov 30, 2025Nov 30, 2025
neurips2025-mind-games-generalization-track-rlgaming
Public
Python
•0•2•0•0•Updated Oct 19, 2025Oct 19, 2025
rlg-tutorial
Public
Tutorials for reinforcement learning in games
Jupyter Notebook
•3•3•0•0•Updated Oct 13, 2025Oct 13, 2025
muzero-decoder
Public
[IEEE TAI] Interpretable MuZero with a decoder that reconstructs observations from hidden states for demystifying planning
go reinforcement-learning decoder
go reinforcement-learning decoder deep-reinforcement-learning gomoku atari monte-carlo-tree-search interpretability explainable-ai explainability
C++
•0•1•0•0•Updated Aug 29, 2025Aug 29, 2025
restnet
Public
[IJCAI 2025] ResTNet: a network that combines residual networks and Transformers to bridge local and global knowledge in board games
go hex reinforcement-learning
go hex reinforcement-learning transformer mcts monte-carlo-tree-search board-games alphazero gumbel-alphazero
Python
•
GNU General Public License v3.0
•0•1•0•0•Updated Jul 18, 2025Jul 18, 2025
optionzero
Public
[ICLR 2025 Oral] OptionZero: A method for autonomously discovering and utilizing options in the MuZero algorithm
reinforcement-learning deep-reinforcement-learning mcts
reinforcement-learning deep-reinforcement-learning mcts atari monte-carlo-tree-search muzero
C++
•1•23•1•0•Updated May 18, 2025May 18, 2025
strength-estimator
Public
[ICLR 2025] A strength system that can estimate the strength from games and provide various playing strengths while simultaneously offer a human-like behavior
go machine-learning chess
go machine-learning chess deep-learning mcts human-computer-interaction monte-carlo-tree-search bradley-terry-model human-like-ai
C++
•
GNU General Public License v3.0
•1•7•1•0•Updated Feb 26, 2025Feb 26, 2025
online-fine-tuning-solver
Public
[NeurIPS 2023] An online fine-tuning game solver for 7x7 Killall-Go
go mcts alphazero
go mcts alphazero game-solver gumbel-alphazero game-solving killall-go proof-cost-network
C++
•0•6•0•0•Updated Oct 30, 2023Oct 30, 2023