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 up- dated 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 test beds 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.
Original language | English |
---|---|
Journal | EAI International Conference on Bio-inspired Information and Communications Technologies (BICT) |
DOIs | |
Publication status | Published - 2015 |
Externally published | Yes |
Event | 9th EAI International Conference on Bio-Inspired Information and Communications Technologies, BICT 2015 - New York City, United States Duration: Dec 3 2015 → Dec 5 2015 |
Keywords
- Analysis
- Internal reward
- Multi-Agent system
- Q-learning
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Networks and Communications
- Hardware and Architecture
- Software
- Neuroscience (miscellaneous)