Exploració per altres contribucions "Martín Muñoz, Mario"
Ara es mostren els items 21-36 de 36
-
Learning recursive goal proposal: a hierarchical reinforcement learning approach
(Universitat Politècnica de Catalunya, 2021-04-28)
Projecte Final de Màster Oficial
Accés obert
Realitzat a/amb: Universitat de Barcelona / Universitat Rovira i Virgili. Escola Tècnica Superior d'EnginyeriaReinforcement Learning's unique way of learning has led to remarkable successes like Alpha Zero or Alpha Go, mastering the games of Chess and Go, and being able to beat the respective World Champions. Notwithstanding, ... -
Learning to run naturally: guiding policies with the Spring-Loaded Inverted Pendulum
(Universitat Politècnica de Catalunya, 2021-04-28)
Projecte Final de Màster Oficial
Accés obert
Realitzat a/amb: Universitat de Barcelona / Universitat Rovira i VirgiliIn this work, we proposed a new approach for learning legged locomotion for any legged robot, in the sagittal plane, by using a combination of classical control techniques and reinforcement learning. Specifically, we use ... -
Learning to safely drive using Reinforcement Learning
(Universitat Politècnica de Catalunya, 2021-04-28)
Projecte Final de Màster Oficial
Accés obert
Realitzat a/amb: Universitat de Barcelona / Universitat Rovira i VirgiliThe autonomous driving research area has gained popularity over the past decade, even more with the launch of the first autonomous vehicle from Tesla, Inc. Different research branches are currently being studied, and one ... -
Leveraging MARL techniques to speed up learning by decomposing big action spaces
(Universitat Politècnica de Catalunya, 2023-10-20)
Projecte Final de Màster Oficial
Accés obertThis thesis explores the field of multi-agent reinforcement learning (MARL). It presents a solution to tackle the problems single-agent methods face when they cannot solve a task because the action dimensionality is too ... -
Meta reinforcement learning for fast adaptation to changing conditions: application to adaptive optics in large telescopes
(Universitat Politècnica de Catalunya, 2022-10-18)
Projecte Final de Màster Oficial
Accés restringit per acord de confidencialitat -
Multi-agent reinforcement learning for underwater acousting tracking
(Universitat Politècnica de Catalunya, 2022-06-29)
Projecte Final de Màster Oficial
Accés restringit per decisió de l'autor -
Offline reinforcement learning for ambulance dispatch
(Universitat Politècnica de Catalunya, 2023-10-19)
Projecte Final de Màster Oficial
Accés obertThis master's thesis is focused on applying offline reinforcement learning techniques to the ambulance dispatch problem, which involves selecting the most appropriate ambulance to dispatch when an incident occurs. The ... -
On Meta-Reinforcement Learning in task distributions with varying dynamics
(Universitat Politècnica de Catalunya, 2021-04-28)
Projecte Final de Màster Oficial
Accés obert
Realitzat a/amb: Universitat de Barcelona / Universitat Rovira i VirgiliMeta-reinforcement learning has the potential to enable artificial agents to master new skills with improved sample-efficiency by leveraging previous learning experience in tasks that are diverse but share common structure. ... -
RedEye: herramienta libre de bajo coste para facilitar la accesibilidad al ordenador a personas con dificultades motoras
(Universitat Politècnica de Catalunya, 2009-07-07)
Projecte/Treball Final de Carrera
Accés obertActualmente el ordenador es una herramienta tan indispensable que toda persona tendría que tener acceso a ella, ya que se usa en el ámbito domestico, laboral o a nivel formativo. Este proyecto de final de carrera tiene ... -
Regularized approximate policy iteration using kernel for on-line reinforcement learning
(Universitat Politècnica de Catalunya, 2015-06-17)
Tesi
Accés obertBy using Reinforcement Learning (RL), an autonomous agent interacting with the environment can learn how to take adequate actions for every situation in order to optimally achieve its own goal. RL provides a general ... -
Reinforcement learning applied as a game mechanic and design element in a custom boss for World of Warcraft
(Universitat Politécnica de Catalunya, 2020-06-23)
Projecte Final de Màster Oficial
Accés obert
Realitzat a/amb: Universitat de Barcelona / Universitat Rovira i VirgiliReinforcement Learning is one of the main categories of Machine Learning algorithms and has seen many applications throughout a wide variety of elds. On the other side, the industry of video games has been in a continuous ... -
Reinforcement learning for portfolio optimization
(Universitat Politècnica de Catalunya, 2022-04-27)
Projecte Final de Màster Oficial
Accés obert
Realitzat a/amb: Universitat Rovira i Virgili / Universitat de BarcelonaIn this study, the potential of using Reinforcement Learning for Portfolio Optimization is investigated, considering the constraints set by the stock market, such as liquidity, slippage, and transaction costs. Five Deep ... -
Resolució d'un problema de planificació industrial mitjançant reinforcement learning
(Universitat Politècnica de Catalunya, 2021-01-10)
Treball Final de Grau
Accés restringit per acord de confidencialitat -
Reverse curriculum hierarchical recursive learning
(Universitat Politècnica de Catalunya, 2022-06-29)
Projecte Final de Màster Oficial
Accés obertThis thesis presents a study on Hierarchical Reinforcement Learning, where several different approaches for learning are researched, developed and tested. Specifically, the algorithm Reverse Curriculum Vicinity Learning ... -
Speeding up Reinforcement Learning with Learned Models
(Universitat Politècnica de Catalunya, 2019-10-16)
Projecte Final de Màster Oficial
Accés obertIn 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 ... -
Videojoc de realitat virtual en Unity
(Universitat Politècnica de Catalunya, 2017-07)
Treball Final de Grau
Accés restringit per decisió de l'autorEn el Treball Final de Grau que s’exposa a continuació, s’ha realitzat el videojoc Carpark amb la finalitat per l’autor d’assolir coneixements sobre Realitat Virtual per augmentar els coneixements en la matèria. Aquesta ...