AlphaZero is a powerful reinforcement learning algorithm based on approximate policy
iteration and tree search. However, AlphaZero can fail to improve its policy network, if not …

Games with large branching factors pose a significant challenge for game tree search
algorithms. In this paper, we address this problem with a sampling strategy for Monte Carlo …

Actions description languages (ADLs), such as STRIPS, PDDL, and RDDL specify the input
format for planning algorithms. Unfortunately, their syntax is familiar to planning experts only …

Sequential decision problems are often approximately solvable by simulating possible future
action sequences. Metalevel decision procedures have been developed for selecting which …

We develop a new algorithm for online planning in large scale sequential decision problems
that improves upon the worst case efficiency of UCT. The idea is to augment Monte-Carlo …

Abstract Monte-Carlo Tree Search (MCTS) methods, such as Upper Confidence Bound
applied to Trees (UCT), are instrumental to automated planning techniques. However, UCT …

We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for
planning in a Markov Decision Process in which transitions have a finite support. We prove …

Decision trees (DTs) are a widely used prediction tool, owing to their interpretability.
Standard learning methods follow a locally optimal approach that trades off prediction …

Many decisions involve choosing an uncertain course of action in deep and wide decision
trees, as when we plan to visit an exotic country for vacation. In these cases, exhaustive …

Evaluating the future consequences of actions is achievable by simulating a mental search
tree into the future. Expanding deep trees, however, is computationally taxing. Therefore …