Skip to Main content Skip to Navigation
Conference papers

Towards a Learning Agent Architecture for Cross-Map Transfer

Cédric Herpson 1 Vincent Corruble 1
1 SMA - Systèmes Multi-Agents
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : The capacity to apply knowledge in a context different than the one in which it was learned is still an open research question within the area of learning agents. This paper specifically addresses the issue of transfer of knowledge acquired through online learning in a partially observable environment characterized by its 2D geographical configuration. We propose an autonomous agent architecture combining an agent-centered representation and the supervised and unsupervised learning of discriminating concepts to achieve efficient cross-map transfer. Our preliminary experiments on a grid-world environment where two agents duel each other show that the agent’s performances are improved through learning, including when it is tested on a map it has not yet seen.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01296327
Contributor : Lip6 Publications <>
Submitted on : Thursday, March 31, 2016 - 5:47:30 PM
Last modification on : Thursday, March 21, 2019 - 1:00:41 PM

Identifiers

  • HAL Id : hal-01296327, version 1

Citation

Cédric Herpson, Vincent Corruble. Towards a Learning Agent Architecture for Cross-Map Transfer. 14th Portuguese Conference on Artificial Intelligence, Oct 2009, Aveiro, Portugal. pp.379-390. ⟨hal-01296327⟩

Share

Metrics

Record views

125