Convex Regularization in Monte-Carlo Tree Search

Abstract

Monte-Carlo planning and Reinforcement Learning (RL) are essential to sequential decision making. The recent AlphaGo and AlphaZero algorithms have shown how to successfully combine these two paradigms in order to solve large scale sequential decision problems. These methodologies exploit a variant of the well-known UCT algorithm to trade off exploitation of good actions and exploration of unvisited states, but their empirical success comes at the cost of poor sample-efficiency and high computation time. In this paper, we overcome these limitations by considering convex regularization in Monte-Carlo Tree Search (MCTS), which has been successfully used in RL to efficiently drive exploration. First, we introduce a unifying theory on the use of generic convex regularizers in MCTS, deriving the regret analysis and providing guarantees of exponential convergence rate. Second, we exploit our theoretical framework to introduce novel regularized backup operators for MCTS, based on the relative entropy of the policy update, and on the Tsallis entropy of the policy. Finally, we empirically evaluate the proposed operators in AlphaGo and AlphaZero on problems of increasing dimensionality and branching factor, from a toy problem to several Atari games, showing their superiority w.r.t. representative baselines.

References in corpus (12)

• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Trust Region Policy Optimization
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Equivalence Between Policy Gradients and Soft Q-Learning
• Bandit Algorithms for Tree Search
• A Theory of Regularized Markov Decision Processes
• Differentiable Dynamic Programming for Structured Prediction and Attention
• Monte-Carlo Tree Search as Regularized Policy Optimization
• Reinforcement Learning via Fenchel-Rockafellar Duality
• Fighting Bandits with a New Kind of Smoothness
• Bayesian Inference in Monte-Carlo Tree Search
• Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value Functions