opendilab /LightZero[NeurIPS 2023焦点] LightZero:一般顺序决策场景中蒙特卡罗树搜索的统一基准(令人敬畏的MCTS) Python1660#alpha-beta-pruning#alphazero#atari#board-game#board-games#continuous-control原文站内解读 →
rlglab /minizero[IEEE ToG] MiniZero: An AlphaZero and MuZero Training Framework C++144#alphazero#deep-reinforcement-learning#gumbel-alphazero#gumbel-muzero#mcts#muzero站内解读 →