Designing Internal Reward of Reinforcement Learning Agents in Multi-Step Dilemma Problem | Zendy

Y. Ichikawa | Zendy; Keiki Takadama | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Designing Internal Reward of Reinforcement Learning Agents in Multi-Step Dilemma Problem

Author(s) -

Y. Ichikawa,

Keiki Takadama

Publication year - 2013

Publication title -

journal of advanced computational intelligence and intelligent informatics

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.172

H-Index - 20

eISSN - 1343-0130

pISSN - 1883-8014

DOI - 10.20965/jaciii.2013.p0926

Subject(s) - reinforcement learning , dilemma , computer science , convergence (economics) , value (mathematics) , reinforcement , reward system , mathematical optimization , artificial intelligence , order (exchange) , machine learning , mathematics , psychology , social psychology , economics , geometry , finance , psychotherapist , economic growth

This paper proposes the reinforcement learning agent that estimates internal rewards using external rewards in order to avoid conflict in multi-step dilemma problem. Intensive simulation results have revealed that the agent succeeds in avoiding local convergence and obtains a behavior policy for reaching a higher reward by updating the Q-value using the value that is subtracted the average reward from an external reward.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research