Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
A teaching method for reinforcement learning
ML92 Proceedings of the ninth international workshop on Machine learning
Creating advice-taking reinforcement learners
Machine Learning - Special issue on reinforcement learning
Fuzzy Sets and Systems - Special issue on fuzzy optimization
Genetic programming: an introduction: on the automatic evolution of computer programs and its applications
Machine Learning
Strongly Typed Genetic Programming in Evolving Cooperation Strategies
Proceedings of the 6th International Conference on Genetic Algorithms
Mutually Supervised Learning in Multiagent Systems
IJCAI '95 Proceedings of the Workshop on Adaption and Learning in Multi-Agent Systems
Fuzzy classification trees for data analysis
Fuzzy Sets and Systems
Genetic programming: a paradigm for genetically breeding populations of computer programs to solve problems
On integrating apprentice learning and reinforcement learning
On integrating apprentice learning and reinforcement learning
Accelerating reinforcement learning through imitation
Accelerating reinforcement learning through imitation
Multiagent Traffic Management: A Reservation-Based Intersection Control Mechanism
AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 2
Learning from Multiple Sources
AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 3
Cooperative learning using advice exchange
Adaptive agents and multi-agent systems
Evolving an expert checkers playing program without using humanexpertise
IEEE Transactions on Evolutionary Computation
Hi-index | 0.00 |
The objective of this work is to determine how/if learning agents can benefit from exchanging information during learning in problems where each team uses a different learning algorithm. In recent studies several problems were exposed, such as lack of coordination, exchange of useless information and difficulties in the adequate choice of advisors. In this work we propose new solutions and test them in two different domains (predator-prey and traffic-control). Our solutions involve hybrid algorithms derived from Q-Learning and Evolutionary Algorithms. Results indicate that some combinations of learning algorithms are more suited to the use of external information than others and that the difference in the results achieved, with and without communication, is problem dependent. The results also show that, in situations where communication is useful, the gain in quality and learning-time can be significant if the right combination of techniques is used to process external information.