Learn your opponent's strategy (in polynomial time)!
- Yishay MorAffiliated withComputer Science Department, Hebrew University
- , Claudia V. GoldmanAffiliated withComputer Science Department, Hebrew University
- , Jeffrey S. RosenscheinAffiliated withComputer Science Department, Hebrew University
Agents that interact in a distributed environment might increase their utility by behaving optimally given the strategies of the other agents. To do so, agents need to learn about those with whom they share the same world.
This paper examines interactions among agents from a game theoretic perspective. In this context, learning has been assumed as a means to reach equilibrium. We analyze the complexity of this learning process. We start with a restricted two-agent model, in which agents are represented by finite automata, and one of the agents plays a fixed strategy. We show that even with this restrictions, the learning process may be exponential in time.
We then suggest a criterion of simplicity, that induces a class of automata that are learnable in polynomial time.
KeywordsDistributed Artificial Intelligence Learning repeated games automata
- Learn your opponent's strategy (in polynomial time)!
- Book Title
- Adaption and Learning in Multi-Agent Systems
- Book Subtitle
- IJCAI'95 Workshop Montréal, Canada, August 21, 1995 Proceedings
- pp 164-176
- Print ISBN
- Online ISBN
- Series Title
- Lecture Notes in Computer Science
- Series Volume
- Series Subtitle
- Lecture Notes in Artificial Intelligence
- Series ISSN
- Springer Berlin Heidelberg
- Copyright Holder
- Additional Links
- Distributed Artificial Intelligence
- repeated games
- Industry Sectors
To view the rest of this content please follow the download PDF link above.