Randomness conservation inequalities; information and independence in mathematical theories
Information and Control
Neural network learning and expert systems
Neural network learning and expert systems
Genetic programming: on the programming of computers by means of natural selection
Genetic programming: on the programming of computers by means of natural selection
Simplifying neural networks by soft weight-sharing
Neural Computation
An introduction to Kolmogorov complexity and its applications
An introduction to Kolmogorov complexity and its applications
Reinforcement learning for robots using neural networks
Reinforcement learning for robots using neural networks
TD-Gammon, a self-teaching backgammon program, achieves master-level play
Neural Computation
Incremental multi-step Q-learning
Machine Learning - Special issue on reinforcement learning
Machine Learning - Special issue on inductive transfer
Reinforcement learning with self-modifying policies
Learning to learn
Neuro-Dynamic Programming
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Correlating Internal Parameters and External Performance: Learning Soccer Agents
ECAI '96 Selected papers from the Workshop on Distributed Artificial Intelligence Meets Machine Learning, Learning in Multi-Agent Environments
ECAI '96 Selected papers from the Workshop on Distributed Artificial Intelligence Meets Machine Learning, Learning in Multi-Agent Environments
A Representation for the Adaptive Generation of Simple Sequential Programs
Proceedings of the 1st International Conference on Genetic Algorithms
ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Adaptation and Learning in Multi-Agent Systems: Some Remarks and a Bibliography
IJCAI '95 Proceedings of the Workshop on Adaption and Learning in Multi-Agent Systems
Co-evolving Soccer Softbot Team Coordination with Genetic Programming
RoboCup-97: Robot Soccer World Cup I
Probabilistic incremental program evolution
Evolutionary Computation
Team-partitioned, opaque-transition reinforcement learning
Proceedings of the third annual conference on Autonomous Agents
Reinforcement Learning Soccer Teams with Incomplete World Models
Autonomous Robots
Rationality Assumptions and Optimality of Co-learning
PRIMA '00 Proceedings of the Third Pacific Rim International Workshop on Multi-Agents: Design and Applications of Intelligent Agents
Communication and Interaction with Learning Agents in Virtual Soccer
VW '00 Proceedings of the Second International Conference on Virtual Worlds
Optimal Ordered Problem Solver
Machine Learning
A multi-agent system integrating reinforcement learning, bidding and genetic algorithms
Web Intelligence and Agent Systems
Cooperative Multi-Agent Learning: The State of the Art
Autonomous Agents and Multi-Agent Systems
Shaping multi-agent systems with gradient reinforcement learning
Autonomous Agents and Multi-Agent Systems
ECCBR '08 Proceedings of the 9th European conference on Advances in Case-Based Reasoning
Hi-index | 0.00 |
We use simulated soccer to study multiagent learning. Each team‘s players (agents) share action set and policy, but may behave differently due to position-dependent inputs. All agents making up a team are rewarded or punished collectively in case of goals. We conduct simulations with varying team sizes, and compare several learning algorithms: TD-Q learning with linear neural networks (TD-Q), Probabilistic Incremental Program Evolution (PIPE), and a PIPE version that learns by coevolution (CO-PIPE). TD-Q is based on learning evaluation functions (EFs) mapping input/action pairs to expected reward. PIPE and CO-PIPE search policy space directly. They use adaptive probability distributions to synthesize programs that calculate action probabilities from current inputs. Our results show that linear TD-Q encounters several difficulties in learning appropriate shared EFs. PIPE and CO-PIPE, however, do not depend on EFs and find good policies faster and more reliably. This suggests that in some multiagent learning scenarios direct search in policy space can offer advantages over EF-based approaches.