dc.contributor.author | Jacob, D. | |
dc.contributor.author | Polani, D. | |
dc.contributor.author | Nehaniv, C.L. | |
dc.date.accessioned | 2008-06-10T10:02:48Z | |
dc.date.available | 2008-06-10T10:02:48Z | |
dc.date.issued | 2004 | |
dc.identifier.citation | Jacob , D , Polani , D & Nehaniv , C L 2004 , ' Improving Learning for Embodied Agents in Dynamic--Environments by State Factorisation ' , Lecture Notes in Artificial Intelligence (LNAI) , vol. 2004 . | |
dc.identifier.issn | 2945-9133 | |
dc.identifier.other | PURE: 96535 | |
dc.identifier.other | PURE UUID: e27d8fd9-a9fe-4421-bde0-831159bc4e49 | |
dc.identifier.other | dspace: 2299/2074 | |
dc.identifier.other | ORCID: /0000-0002-3233-5847/work/86098027 | |
dc.identifier.uri | http://hdl.handle.net/2299/2074 | |
dc.description.abstract | A new reinforcement learning algorithm designed--specifically for robots and embodied systems--is described. Conventional reinforcement learning methods intended for learning general tasks suffer from a number of disadvantages in this domain including slow learning speed, an inability--to generalise between states, reduced performance--in dynamic environments, and a lack of scalability. Factor-Q, the new algorithm, uses factorised state and action, coupled with multiple structured rewards, to address these issues. Initial experimental results demonstrate that Factor-Q is able to learn as efficiently in dynamic as in static environments, unlike conventional methods. Further, in the specimen task,--obstacle avoidance is improved by over two orders--of magnitude compared with standard Qlearning. | en |
dc.language.iso | eng | |
dc.relation.ispartof | Lecture Notes in Artificial Intelligence (LNAI) | |
dc.title | Improving Learning for Embodied Agents in Dynamic--Environments by State Factorisation | en |
dc.contributor.institution | School of Computer Science | |
dc.contributor.institution | Centre for Computer Science and Informatics Research | |
dc.contributor.institution | Department of Computer Science | |
dc.contributor.institution | Adaptive Systems | |
dc.contributor.institution | School of Physics, Engineering & Computer Science | |
dc.contributor.institution | Centre for Future Societies Research | |
dc.contributor.institution | Science & Technology Research Institute | |
dc.description.status | Peer reviewed | |
rioxxterms.type | Journal Article/Review | |
herts.preservation.rarelyaccessed | true | |