paper-with-me

홈 › Papers

Scale-Adaptive Balancing of Exploration and Exploitation in Classical Planning

2023-05-16 · Stephen Wissow, Masataro Asai

Balancing exploration and exploitation has been an important problem in both game tree search and automated planning. However, while the problem has been extensively analyzed within the Multi-Armed Bandit (MAB) literature, the planning community has had limited success when attempting to apply those results. We show that a more detailed theoretical understanding of MAB literature helps improve existing planning algorithms that are based on Monte Carlo Tree Search (MCTS) / Trial Based Heuristic Tree Search (THTS). In particular, THTS uses UCB1 MAB algorithms in an ad hoc manner, as UCB1's theoretical requirement of fixed bounded support reward distributions is not satisfied within heuristic search for classical planning. The core issue lies in UCB1's lack of adaptations to the different scales of the rewards. We propose GreedyUCT-Normal, a MCTS/THTS algorithm with UCB1-Normal bandit for agile classical planning, which handles distributions with different scales by taking the reward variance into consideration, and resulted in an improved algorithmic performance (more plans found with less node expansions) that outperforms Greedy Best First Search and existing MCTS/THTS-based algorithms (GreedyUCT,GreedyUCT*).

📄 PDF Abstract BibTeX arXiv:2305.09840

Code (0)

등록된 구현이 없습니다.

Tasks

Heuristic Search

Methods 이 논문이 사용한 방법론

HOC 설명 없음

Similar Papers 제목 키워드 기반

Exploration versus exploitation in reinforcement learning: a stochastic control approach

2018-12-04 · Haoran Wang, Thaleia Zariphopoulou, Xunyu Zhou

We consider reinforcement learning (RL) in continuous time and study the problem of achieving the best trade-off between exploration of a black box environment and exploitation of current knowledge. We propose an entropy…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Novel Adaptive Genetic Algorithm Sample Consensus

2017-11-26 · Ehsan Shojaedini, Mahshid Majd, Reza Safabakhsh

Random sample consensus (RANSAC) is a successful algorithm in model fitting applications. It is vital to have strong exploration phase when there are an enormous amount of outliers within the dataset. Achieving a proper …

Random Walk on Bézier Curves for Global Optimization

2026-06-25 · Jinpeng Wang, Xingguo Xu, Yujing Sun, Jiguang Yu 외 arxiv

Balancing exploration and exploitation remains a central challenge in metaheuristic optimization. To address this issue, this paper proposes Bézier Walk Evolution (BWE), a geometry-driven optimization framework that refo…

Dynamic Exploration-Exploitation Trade-Off in Active Learning Regression with Bayesian Hierarchical Modeling

2023-04-16 · Upala Junaida Islam, Kamran Paynabar, George Runger, Ashif Sikandar Iquebal

Active learning provides a framework to adaptively query the most informative experiments towards learning an unknown black-box function. Various approaches of active learning have been proposed in the literature, howeve…

Active Learningregression

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

2025-08-14 · Zhipeng Chen, Xiaobo Qin, Youbin Wu, Yue Ling 외 arxiv

Reinforcement learning with verifiable rewards (RLVR), which typically adopts Pass@1 as the reward, has faced the issues in balancing exploration and exploitation, causing policies to prefer conservative actions, converg…

Reinforcement Learning