.png){kind=icon}
返回
CAGE: A Curiosity-Driven Graph-Based Explore-Exploit Algorithm for Solving Deterministic Environment MDPs With Limited Episode Problem
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3468027.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The explore-exploit dilemma in Markov Decision Processes (MDPs) is a fundamental challenge, especially in deterministic environments akin to real-world scenarios. Balancing exploration and exploitation within limited episodes is crucial to optimize decision-making. Despite existing research, challenges like parameter sensitivity, lack of global optimality, and inefficient exploration of low-value regions remain. We introduce the Curiosity-driven Algorithm based on Graph for Exploration (CAGE), which addresses these issues through a graph-based framework. CAGE includes two variants: CAGE-greedy, ensuring optimal solutions with ample episodes, and CAGE-centrality, prioritizing significant states in limited episodes. Key contributions include eliminating parameter sensitivity, guaranteeing global optimality, and enhancing exploration efficiency. To validate the performance of the CAGE algorithm series, we design a grid world experiment. The experimental results demonstrate that the CAGE algorithm outperforms a comparative algorithm, indicating its feasibility for implementation in the industry and its high level of explainability. Experimental results validate CAGE's effectiveness in complex environments.
Keyword:
Bayes methods
Classification algorithms
Heuristic algorithms
Uncertainty
Tuning
Sensitivity
Probability distribution
Markov processes
Graph theory
Markov decision process
graph theory
curiosity-driven
explore-exploit problem
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Does it take older adults longer than younger adults to perceptually segregate a speech target from a background masker?在感知上将语音目标与背景掩蔽器隔离开来是否需要老年人比年轻人更长的时间？
.png){kind=icon}
PREAI
分享收藏
ALIPHATIC AND TRITERPENOIC PRODUCTS OF ETHER EXTRACTS SAPONIFICATION OF POPULUS NIGRA L.脂肪族和三萜类产物：来自 Populus nigra L. 醚提取物的皂化物OAAI
OAAI分享收藏
查看更多内容