Automatic abstraction controller in reinforcement learning agent via automata |
| |
| Affiliation: | 1. College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China;2. School of Electrical and Electronic Engineering, East China Jiaotong University, Nanchang 330013, China;3. Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124, China;1. School of Computer and Information Science, Southwest University, Chongqing 400715, China;2. College of Computer Science, Chongqing University, Chongqing 400044, China;3. Institute of Business Intelligence and Knowledge Discovery, Guangdong University of Foreign Studies, Guangzhou 510006, China;4. School of Engineering, Vanderbilt University, Nashville, TN 37235, USA |
| |
| Abstract: | Reinforcement learning (RL) for solving large and complex problems faces the curse of dimensions problem. To overcome this problem, frameworks based on the temporal abstraction have been presented; each having their advantages and disadvantages. This paper proposes a new method like the strategies introduced in the hierarchical abstract machines (HAMs) to create a high-level controller layer of reinforcement learning which uses options. The proposed framework considers a non-deterministic automata as a controller to make a more effective use of temporally extended actions and state space clustering. This method can be viewed as a bridge between option and HAM frameworks, which tries to suggest a new framework to decrease the disadvantage of both by creating connection structures between them and at the same time takes advantages of them. Experimental results on different test environments show significant efficiency of the proposed method. |
| |
| Keywords: | Reinforcement learning Hierarchical reinforcement learning Cluster Multi-agent learning |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
