4 accepted papers
We study an efficient implementation of Multi-Armed Bandit (MAB)-based Monte-Carlo Tree Search (MCTS) for classical planning. One weakness of MCTS is that it spends a significant time in deciding which node to expand next. While selecting a node from an OPEN list with N nodes has O(1) runtime comple
Despite being successful in board games and reinforcement learning (RL), Monte Carlo Tree Search (MCTS) combined with Multi Armed Bandit (MAB) has seen limited success in domain-independent classical planning until recently. Previous work (Wissow and Asai, 2024) showed that UCB1, designed for bounde
In recent years, there has been growing interest in utilizing modern machine learning techniques to learn heuristic functions for forward search algorithms. Despite this, there has been little theoretical understanding of what they should learn, how to train them, and why we do so. This lack of unde…
We achieved a new milestone in the difficult task of enabling agents to learn about their environment autonomously. Our neuro-symbolic architecture is trained end-to-end to produce a succinct and effective discrete state transition model from images alone. Our target representation (the Planning Dom…