Abstract
Collecting and maintaining accurate world knowledge in a dynamic, complex, competitive, and stochastic environment such as RoboCup 3D Soccer Simulation is a challenging task. Knowledge should be learned in real-time with time constraints. We use recently introduced Off-Policy Gradient Descent algorithms in Reinforcement Learning that illustrate learnable knowledge representations for dynamic role assignments. The results show that the agents have learned competitive policies against the top teams from RoboCup 2012 for three vs three, five vs five, and seven vs seven agents. We have explicitly used subset of agents to identify the dynamics and the semantics for which the agents learn to maximize their performance measures, and to gather knowledge about different objectives so that all agents participate effectively within the team.
Original language | English (US) |
---|---|
Title of host publication | AAMAS 2013 Workshop on Adaptive and Learning Agents, ALA 2013 |
Publisher | AAMAS |
ISBN (Print) | 9781943580125 |
State | Published - 2013 |
Event | AAMAS 2013 Workshop on Adaptive and Learning Agents, ALA 2013 - Saint Paul, United States Duration: May 6 2013 → May 7 2013 |
Other
Other | AAMAS 2013 Workshop on Adaptive and Learning Agents, ALA 2013 |
---|---|
Country | United States |
City | Saint Paul |
Period | 5/6/13 → 5/7/13 |
Keywords
- Dynamic role assignment function
- GQ(λ)
- Greedy-GQ(λ)
- Off-Policy Prediction and Control
- Reinforcement learning
ASJC Scopus subject areas
- Artificial Intelligence
- Software