Published January 1, 2017 | Version v1
Conference paper Open

A Concept Filtering Approach for Diverse Density to Discover Subgoals in Reinforcement Learning

  • 1. Middle East Tech Univ, Dept Comp Engn, TR-06531 Ankara, Turkey
  • 2. STM Def Technol Engn & Trade Inc, TR-06530 Ankara, Turkey

Description

In the reinforcement learning context, subgoal discovery methods aim to find bottlenecks in problem state space so that the problem can naturally be decomposed into smaller subproblems. In this paper, we propose a concept filtering method that extends an existing subgoal discovery method, namely diverse density, to be used for both fully and partially observable RL problems. The proposed method is successful in discovering useful subgoals with the help of multiple instance learning. Compared to the original algorithm, the resulting approach runs significantly faster without sacrificing the solution quality. Moreover, it can effectively be employed to find observational bottlenecks of problems with perceptually aliased states.

Files

bib-0b7c25be-e29b-475e-a8d9-bff5dc6ff35b.txt

Files (229 Bytes)

Name Size Download all
md5:a9cf7691ac1c90844531d08de20ab505
229 Bytes Preview Download