Inverse reinforcement learning with linearly-solvable MDPs for multiple reward functions
Treball fi de màster de: Master in Intelligent Interactive Systems. Tutors: Anders Jonsson, Vicenç Gómez, Mario Ceresa
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2023 |
| País: | España |
| Institución: | Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| Repositorio: | Recercat. Dipósit de la Recerca de Catalunya |
| OAI Identifier: | oai:recercat.cat:10230/58063 |
| Acceso en línea: | http://hdl.handle.net/10230/58063 |
| Access Level: | acceso abierto |
| Palabra clave: | Linearly solvable Markov Decision Process Inverse Reinforcement Learn- Ing Multiple Rewards Non-parametric Bayesian Learning Linearly solvable Markov Decision Process Inverse Reinforcement Learning Multiple Rewards Non-parametric Bayesian Learning |
| Sumario: | Treball fi de màster de: Master in Intelligent Interactive Systems. Tutors: Anders Jonsson, Vicenç Gómez, Mario Ceresa |
|---|