Earticle

초록

영어

Reinforcement Learning is an area of machine learning that studies the problem of solving sequential decision making problems. The agent must learn behavior through trial-and-error interaction with a dynamic environment. Learning efficiently in large scale problems and complex tasks demands a decomposition of the original complex task into simple and smaller subtasks. In this paper, we present a subgoal-based method for automatically creating useful skills in reinforcement Learning. Our method identifies subgoals using a local graph clustering algorithm. The main advantage of the proposed algorithm is that only the local information of the graph is considered to cluster the agent state space. Clustering of the transition graphs corresponding to MDPs can be performed in linear time using the proposed method. Subgoals discovered by the algorithm are then used to generate skills using the option framework. Experimental results show that the proposed subgoal discovery algorithm has a dramatic effect on the learning performance.

목차

Abstract
 1. Introduction
 2. Reinforcement Learning With Option
 3. Proposed Method
 4. Complexity Analysis
 5. Experimental Results
  5.1. Six-room Gridworld
  5.2. Soccer Simulation Test Bed
  5.3 Results
 6. Conclusion
 References

키워드

저자

• Negin Entezari [ Department of Computer Sicence, Amirkabir University of Technology, Tehran, Iran ]
• Mohammad Ebrahim Shiri [ Department of Computer Sicence, Amirkabir University of Technology, Tehran, Iran ]
• Parham Moradi [ University of Kurdistan, Department of Electrical & Computer Engineering, Sanandaj, Iran ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Future Generation Communication and Networking

• 간기

  격월간

• pISSN

  2233-7857

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605