Technical Note: \cal Q-Learning
Machine Learning
Competitive Markov decision processes
Competitive Markov decision processes
The dynamics of reinforcement learning in cooperative multiagent systems
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Neuro-Dynamic Programming
An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Karlsruhe Brainstormers - A Reinforcement Learning Approach to Robotic Soccer
RoboCup 2000: Robot Soccer World Cup IV
Reinforcement Learning for 3 vs. 2 Keepaway
RoboCup 2000: Robot Soccer World Cup IV
A Model of Adaptation in Collaborative Multi-Agent Systems
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study
RoboCup 2006: Robot Soccer World Cup X
Simulation and reinforcement learning with soccer agents
Multiagent and Grid Systems - Innovations in intelligent agent technology
Experimental analysis on Sarsa(λ) and Q(λ) with different eligibility traces strategies
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology - Theoretical advances of intelligent paradigms
Functional knowledge exchange within an intelligent distributed system
ARCS'07 Proceedings of the 20th international conference on Architecture of computing systems
Reinforcement learning of competitive and cooperative skills in soccer agents
Applied Soft Computing
CBR for state value function approximation in reinforcement learning
ICCBR'05 Proceedings of the 6th international conference on Case-Based Reasoning Research and Development
Hi-index | 0.00 |
Our long-term goal is to build teams of agents where the decision making is based completely on Reinforcement Learning (RL) methods. It requires an appropriate modelling of the learning task and the paper describes how robotic soccer can be seen as a multi-agent Markov Decision Process (MMDP). It discusses how optimality of behaviours of agents can be defined and what difficulties one encounters in developing concrete algorithms which are supposed to reach such optimal agent/team policies. We also give an overview of already incorporated algorithms in our 'Karlsruhe Brainstormers' simulator league team and report some results on learning of offensive team behaviour.