Reinforcement learning with temperature distribution based on likelihood function

Norimasa Kobori, Kenji Suzuji, Pitoyo Hartono, Shuji Hashimoto

    Research output: Contribution to journalArticlepeer-review

    2 Citations (Scopus)

    Abstract

    In the existing Reinforcement Learning, it is difficult and time consuming to find appropriate the meta-parameters such as learning rate, eligibility traces and temperature for exploration, in particular on a complicated and large-scale problem, the delayed reward often occurs and causes a difficulty in solving the problem. In this paper, we propose a novel method introducing a temperature distribution for reinforcement learning. In addition to the acquirement of policy based on profit sharing, the temperature is given to each state and is trained by hill-climbing method using likelihood function based on success and failure of the task. The proposed method can reduce the parameter setting according to the given problems. We showed the performance on the grid world problem and the control of Acrobot.

    Original languageEnglish
    Pages (from-to)297-305
    Number of pages9
    JournalTransactions of the Japanese Society for Artificial Intelligence
    Volume20
    Issue number4
    DOIs
    Publication statusPublished - 2005

    Keywords

    • Delayed reward
    • Maximum likelihood estimation
    • Meta-parameter control
    • Profit sharing
    • Reinforcement Learning
    • Temperature distribution

    ASJC Scopus subject areas

    • Artificial Intelligence

    Fingerprint Dive into the research topics of 'Reinforcement learning with temperature distribution based on likelihood function'. Together they form a unique fingerprint.

    Cite this