Speeding up Reinforcement Learning with Learned Models
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.
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2019 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/175740 |
| Acceso en línea: | https://hdl.handle.net/2117/175740 |
| Access Level: | acceso abierto |
| Palabra clave: | Reinforcement learning Algorithms Model Based Reinforcement Learning Hindsight Experience Replay off-policy methods sparse rewards sample efficiency. Aprenentatge per reforç Algorismes Àrees temàtiques de la UPC::Informàtica |
| Sumario: | 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. |
|---|