Abstract | ||
---|---|---|
In this paper, we investigate the use of nested evolution in which each step of one evolutionary process involves running a second evolutionary process. We apply this approach to build a neuroevolution system for reinforcement learning (RL) problems. Genetic programming based on a descriptive encoding is used to evolve the neural architecture, while a nested evolution strategy is used to evolve the needed connection weights. We test this hierarchical evolution on a non-Markovian RL problem involving an autonomous foraging agent, finding that the evolved networks significantly outperform a rule-based agent serving as a control. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1145/1389095.1389141 | GECCO |
Keywords | Field | DocType |
nested evolution,evolutionary process,non-markovian rl problem,needed connection weight,autonomous agent,rule-based agent,genetic programming,descriptive encoding,autonomous foraging agent,hierarchical evolution,nested evolution strategy,neuroevolution,rule based,reinforcement learning,evolution strategy | Evolutionary acquisition of neural topologies,Autonomous agent,Computer science,Genetic programming,Evolution strategy,Artificial intelligence,Neuroevolution,Machine learning,Foraging,Encoding (memory),Reinforcement learning | Conference |
Citations | PageRank | References |
1 | 0.36 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jae-Yoon Jung | 1 | 297 | 31.94 |
James A. Reggia | 2 | 1000 | 276.13 |