Reinforcement Learning with Internal Reward for Multi-Agent Cooperation: A Theoretical Approach
Journal Title: EAI Endorsed Transactions on Collaborative Computing - Year 2016, Vol 2, Issue 8
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.
Authors and Affiliations
Fumito Uwano, Naoki Tatebe, Masaya Nakata, Keiki Takadama, Tim Kovacs
Keywords
Related Articles
- EP ID EP45716
- DOI http://dx.doi.org/10.4108/eai.3-12-2015.2262878
- Views 339
- Downloads 0
Welcome Message from the Editor-in-Chief.
No Abstract
A System for Multimodal Interaction with Kinect-Enabled Virtual Windows
Commercial off-the-shelf gaming devices (e.g. such as Kinect) are demonstrating to have a great potential beyond their initial service purpose. In particular, when integrated within the environment or as part of smart ob...
Analysis of Differential Synchronisation’s Energy Consumption on Mobile Devices
Synchronisation algorithms are central to collaborative editing software. As collaboration is increasingly mediated by mobile devices, the energy eÿciency for such algorithms is interest to a wide community of applicatio...
A Collaboration Model for Community-Based Software Development with Social Machines
Crowdsourcing is generally used for tasks with minimal coordination, providing limited support for dynamic reconfiguration. Modern systems, exemplified by social ma chines, are subject to continual flux in both the clien...
Collaborating with executable content across space and time
Executable content is of growing importance in many domains. How does one share and archive such content at Internet-scale for spatial and temporal collaboration? Spatial collaboration refers to the classic concept of us...