Sample-based tree search (SBTS) is an approach to solving Markov decision problems
based on constructing a lookahead search tree using random samples from a generative …

Monte Carlo tree search (MCTS) algorithms are a popular approach to online decision-
making in Markov decision processes (MDPs). These algorithms can, however, perform …

We consider the problem of using a heuristic policy to improve the value approximation by
the Upper Confidence Bound applied in Trees (UCT) algorithm in non-adversarial settings …

Abstract Monte Carlo Tree Search (MCTS) is a family of directed search algorithms that has
gained widespread attention in recent years. Despite the vast amount of research into …

Online solvers for partially observable Markov decision processes have difficulty scaling to
problems with large action spaces. Monte Carlo tree search with progressive widening …

Abstract Monte-Carlo Tree Search (MCTS) algorithms estimate the value of MDP states
based on rewards received by performing multiple random simulations. MCTS algorithms …

Monte-Carlo tree search is based on contiguous rollouts. Since not all samples within a
rollout necessarily provide relevant information, contiguous rollouts may be wasteful as …

Abstract Monte-Carlo Tree Search, especially UCT and its POMDP version POMCP, have
demonstrated excellent performanceon many problems. However, to efficiently scale to …

Bayes-optimal behavior, while well-defined, is often difficult to achieve. Recent advances in
the use of Monte-Carlo tree search (MCTS) have shown that it is possible to act …

A key problem in reinforcement learning is finding a good balance between the need to
explore the environment and the need to gain rewards by exploiting existing knowledge …