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
SocialCloudShare: a Facebook Application for a Relationship-based Information Sharing in the Cloud
In last few years, Online Social Networks (OSNs) have become one of the most used platforms for sharing data (e.g., pictures, short texts) on the Internet. Nowadays Facebook and Twitter are the most popular OSN providers...
Achieving Security Assurance with Assertion-based Application Construction
Modern software applications are commonly built by leveraging pre-fabricated modules, e.g. application programming interfaces (APIs), which are essential to implement the desired functionalities of software applications,...
Tracing Coordination and Cooperation Structures via Semantic Burst Detection
Developing technologies that support collaboration requires understanding how knowledge and expertise are shared and distributed among community members. We explore two forms of knowledge distribution structures, coordin...
A Tuple Space for Data Sharing in Robot Swarms
In this paper, we present a system to allow a swarm of robots to agree on a set of (key,value) pairs. This system enables a form of information sharing that has the potential to be an asset for coordination in complex en...
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...