Mostra el registre d'ítem simple
Speeding up Reinforcement Learning with Learned Models
dc.contributor | Martín Muñoz, Mario |
dc.contributor.author | Pou Mulet, Bartomeu |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
dc.date.accessioned | 2020-01-26T21:35:58Z |
dc.date.available | 2020-01-26T21:35:58Z |
dc.date.issued | 2019-10-16 |
dc.identifier.uri | http://hdl.handle.net/2117/175740 |
dc.description.abstract | In this master thesis, we have tried to solve two of most prominent Reinforcement Learning problems: sparse rewards and sample efficiency. The combination of Model Based Reinforcement Learning, Hindsight Experience Replay and off-policy methods is the approach we took to solve the problems. |
dc.language.iso | eng |
dc.publisher | Universitat Politècnica de Catalunya |
dc.subject | Àrees temàtiques de la UPC::Informàtica |
dc.subject.lcsh | Reinforcement learning |
dc.subject.lcsh | Algorithms |
dc.subject.other | Model Based Reinforcement Learning |
dc.subject.other | Hindsight Experience Replay |
dc.subject.other | off-policy methods |
dc.subject.other | sparse rewards |
dc.subject.other | sample efficiency. |
dc.title | Speeding up Reinforcement Learning with Learned Models |
dc.type | Master thesis |
dc.subject.lemac | Aprenentatge per reforç |
dc.subject.lemac | Algorismes |
dc.identifier.slug | 143210 |
dc.rights.access | Open Access |
dc.date.updated | 2019-10-28T05:00:50Z |
dc.audience.educationlevel | Màster |
dc.audience.mediator | Facultat d'Informàtica de Barcelona |
dc.audience.degree | MÀSTER UNIVERSITARI EN INTEL·LIGÈNCIA ARTIFICIAL (Pla 2017) |