Abstract
An agent must learn and adapt quickly when playing against other agents. This process is challenging in particular when playing in stochastic environments against other learning agents. In this paper, we introduce a fast and adaptive learning algorithm for repeated stochastic games (FAL-SG). FAL-SG utilizes lossy game abstraction to reduce the state space of the game and facilitate learning and adapting rapidly. We analyze FAL-SG's performance by proving bounds on the abstraction loss and prediction mistakes and show that FAL-SG satisfies three criteria prescribed for multiagent learning algorithms. We successfully establish the robustness and scalability of FAL-SG with extensive theoretical and experimental results.
| Original language | English (US) |
|---|---|
| Title of host publication | 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 |
| Publisher | International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) |
| Pages | 1141-1148 |
| Number of pages | 8 |
| ISBN (Electronic) | 9781634391313 |
| State | Published - 2014 |
| Event | 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 - Paris, France Duration: May 5 2014 → May 9 2014 |
Publication series
| Name | 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 |
|---|---|
| Volume | 2 |
Other
| Other | 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 |
|---|---|
| Country/Territory | France |
| City | Paris |
| Period | 5/5/14 → 5/9/14 |
Bibliographical note
Publisher Copyright:Copyright © 2014, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
Keywords
- Adversarial learning
- Game theory
- Multiagent learning