AI Research 技术调研

标签: sequential-halving

此标签下有1条笔记。

  • 2026年7月16日

    Policy Improvement by Planning with Gumbel (Gumbel MuZero)

    • reinforcement-learning
    • mcts
    • alphazero
    • muzero
    • policy-improvement
    • gumbel-top-k
    • sequential-halving
    • tree-search
    • model-based-rl

  • GitHub