Policy Transfer in Reinforcement Learning with Domain Adaptation using Transition Probability

DOI
  • SATO Rei
    University of Tsukuba RIKEN Center for Advanced Intelligence Project
  • FUKUCHI Kazuto
    University of Tsukuba RIKEN Center for Advanced Intelligence Project
  • SAKUMA Jun
    University of Tsukuba RIKEN Center for Advanced Intelligence Project
  • AKIMOTO Youhei
    University of Tsukuba RIKEN Center for Advanced Intelligence Project

Bibliographic Information

Other Title
  • 強化学習における遷移確率を用いたドメイン適応による方策の転移

Abstract

<p>Reinforcement learning is drawing increasing attentions in real world applications.Since it often takes enormous cost to learn the agent in the real world environment (called target task), pre-training in a low-cost environment such as a simulator (called source task) is gathering attention. In this paper, we focus on the situation where the source and target tasks are different only in the form of state observation. Our proposed method trains encoders mapping state observation to latent representations, and trains a policy that receives a latent representation and output an action.We utilize the transition probability to learn latent representations robust to changes in the form of state observation.This enables transferring the policy learned in the source task to improve the performance in the target task.Experiments show that our method can achieve higher performance when the number of interactions in the target task is limited.</p>

Journal

Keywords

Details 詳細情報について

  • CRID
    1390285300166118400
  • NII Article ID
    130007856956
  • DOI
    10.11517/pjsai.jsai2020.0_2j5gs203
  • Text Lang
    ja
  • Data Source
    • JaLC
    • CiNii Articles
  • Abstract License Flag
    Disallowed

Report a problem

Back to top