Selecting Computations: Theory and Applications
원문 초록
Sequential decision problems are often approximately solvable by simulating possible future action sequences. Metalevel decision procedures have been developed for selecting which action sequences to simulate, based on estimating the expected improvement in decision quality that would result from any particular simulation; an example is the recent work on using bandit algorithms to control Monte Carlo tree search in the game of Go. In this paper we develop a theoretical basis for metalevel decisions in the statistical framework of Bayesian selection problems, arguing (as others have done) that this is more appropriate than the bandit framework. We derive a number of basic results applicable to Monte Carlo selection problems, including the first finite sampling bounds for optimal policies in certain cases; we also provide a simple counterexample to the intuitive conjecture that an optimal policy will necessarily reach a decision in all cases. We then derive heuristic approximations in both Bayesian and distribution-free settings and demonstrate their superiority to bandit-based heuristics in one-shot decision problems and in Go.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in Games
Monte Carlo Tree Search with Boltzmann Exploration
Active Reinforcement Learning for Robust Building Control
Are AlphaZero-like Agents Robust to Adversarial Perturbations?
Conservative Optimistic Policy Optimization via Multiple Importance Sampling
Visualizing MuZero Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.