Multi-Agent Behavior-Based Policy Transfer
Didi, Sabre and Geoff Nitschke (2016) Multi-Agent Behavior-Based Policy Transfer. In Proceedings European Conference on the Applications of Evolutionary Computation (Evostar 2016), pages 181-197, Porto, Portugal.
A key objective of transfer learning is to improve and speedup learning on a target task after training on a different, but related, source task. This study presents a neuro-evolution method that transfers evolved policies within multi-agent tasks of varying degrees of complexity. The method incorporates behavioral diversity (novelty) search as a means to boost the task performance of transferred policies (multi-agent behaviors). Results indicate that transferred evolved multi-agent behaviors are significantly improved in more complex tasks when adapted using behavioral diversity. Comparatively, behaviors that do not use behavioral diversity to further adapt transferred behaviors, perform relatively poorly in terms of adaptation times and quality of solutions in target tasks. Also, in support of previous work, both policy transfer methods (with and without behavioral diversity adaptation), out-perform behaviors evolved in target tasks without transfer learning.
|EPrint Type:||Conference Paper|
|Subjects:||I Computing Methodologies: I.2 ARTIFICIAL INTELLIGENCE|
|Deposited By:||Nitschke, Geoff|
|Deposited On:||23 November 2017|