Abstract

Over the past decade, Monte Carlo Tree Search (MCTS) and specifically Upper Confidence Bound in Trees (UCT) have proven to be quite effective in large probabilistic planning domains. In this paper, we focus on how values are backpropagated in the MCTS tree, and apply complex return strategies from the Reinforcement Learning (RL) literature to MCTS, producing 4 new MCTS variants. We demonstrate that in some probabilistic planning benchmarks from the International Planning Competition (IPC), selecting a MCTS variant with a backup strategy different from Monte Carlo averaging can lead to substantially better results. We also propose a hypothesis for why different backup strategies lead to different performance in particular environments, and manipulate a carefully structured grid-world domain to provide empirical evidence supporting our hypothesis.