Name
Abstract | ||
|---|---|---|
This paper presents MUTANT, a learning system for autonomous agents. MUTANT is an adaptive control architecture founded on genetic techniques and reinforcement learning. The system allows an agent to learn some complex tasks without requiring its designer to fully specify how they should be carried out. An agent behavior is defined by a set of rules, genetically encoded. The rules are evolved over time by a genetic algorithm to synthesize some new better rules according to their respective adaptive function, computed by progressive reinforcements. The system is validated through an experimentation in collective robotics. |
Year | DOI | Venue |
|---|---|---|
1999 | 10.1007/3-540-46695-9_18 | Australian Joint Conference on Artificial Intelligence |
Keywords | Field | DocType |
agent behavior,genetic technique,genetic algorithm,new better rule,genetic learning system,autonomous agent,complex task,adaptive control architecture,collective robotics,reinforcement learning,respective adaptive function,adaptive control,genetics | Autonomous agent,Computer science,Agent behavior,Artificial intelligence,Adaptive control,Mutant,Machine learning,Genetic algorithm,Genetic learning,Robotics,Reinforcement learning | Conference |
Volume | ISSN | ISBN |
1747 | 0302-9743 | 3-540-66822-5 |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Stéphane Calderoni | 1 | 11 | 3.08 |
| P. Marcenac | 2 | 30 | 9.38 |