Description
AlphaZero is a reinforcement learning agent for playing board games such as Go, chess, and shogi.
Papers Using This Method
AlphaZero-Edu: Making AlphaZero Accessible to Everyone2025-04-20AssistanceZero: Scalably Solving Assistance Games2025-04-09Reinforcement Learning and Life Cycle Assessment for a Circular Economy -- Towards Progressive Computer Science2025-03-13Alignment, Agency and Autonomy in Frontier AI: A Systems Engineering Perspective2025-02-20Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks2025-02-19On the Emergence of Thinking in LLMs I: Searching for the Right Intuition2025-02-10Towards Intrinsic Self-Correction Enhancement in Monte Carlo Tree Search Boosted Reasoning via Iterative Preference Learning2024-12-23AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws2024-12-16Mastering NIM and Impartial Games with Weak Neural Networks: An AlphaZero-inspired Multi-Frame Approach2024-11-10Enhancing Chess Reinforcement Learning with Graph Representation2024-10-31Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning2024-10-15ResTNet: Defense against Adversarial Policies via Transformer in Computer Go2024-10-07Maia-2: A Unified Model for Human-AI Alignment in Chess2024-09-30Mastering Chess with a Transformer Model2024-09-18AlphaViT: A Flexible Game-Playing AI for Multiple Games and Variable Board Sizes2024-08-25ShortCircuit: AlphaZero-Driven Circuit Design2024-08-19Structure and Reduction of MCTS for Explainable-AI2024-08-10Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization2024-07-07AlphaZeroES: Direct score maximization outperforms planning loss minimization2024-06-12Learning to Play 7 Wonders Duel Without Human Supervision2024-06-02