Reinforcement Learning with Internal Reward for Multi-Agent Cooperation: A Theoretical Approach

Uwano, Fumito and Tatebe, Naoki and Nakata, Masaya and Takadama, Keiki and Kovacs, Tim (2016) Reinforcement Learning with Internal Reward for Multi-Agent Cooperation: A Theoretical Approach. EAI Endorsed Transactions on Collaborative Computing, 4 (8). e2. ISSN 2312-8623

[img]
Preview
Text (PDF)
eai.3-12-2015.2262878.pdf - Published Version

Download (766kB) | Preview

Abstract

This paper focuses on a multi-agent cooperation which is generally difficult to be achieved without sufficient information of other agents, and proposes the reinforcement learning method that introduces an internal reward for a multi-agent cooperation without sufficient information. To guarantee to achieve such a cooperation, this paper theoretically derives the condition of selecting appropriate actions by changing internal rewards given to the agents, and extends the reinforcement learning methods (Q-learning and Profit Sharing) to enable the agents to acquire the appropriate Q-values updated according to the derived condition. Concretely, the internal rewards change when the agents can only find better solution than the current one. The intensive simulations on the maze problems as one of testbeds have revealed the following implications:(1) our proposed method successfully enables the agents to select their own appropriate cooperating actions which contribute to acquiring the minimum steps towards to their goals, while the conventional methods (i.e., Q-learning and Profit Sharing) cannot always acquire the minimum steps; and (2) the proposed method based on Profit Sharing provides the same good performance as the proposed method based on Q-learning.

Item Type: Article
Uncontrolled Keywords: multi-agent system, analysis, q-learning, internal reward
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
QA75 Electronic computers. Computer science
Depositing User: EAI Editor IV
Date Deposited: 09 Jul 2021 08:26
Last Modified: 09 Jul 2021 08:26
URI: https://eprints.eudl.eu/id/eprint/4284

Actions (login required)

View Item View Item