1 resultado para reaching
em Universitat de Girona, Spain
Filtro por publicador
- Aberystwyth University Repository - Reino Unido (3)
- Adam Mickiewicz University Repository (3)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (3)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (1)
- Aquatic Commons (39)
- Archive of European Integration (6)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (18)
- Aston University Research Archive (3)
- B-Digital - Universidade Fernando Pessoa - Portugal (3)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (2)
- Biblioteca Digital de la Universidad Católica Argentina (3)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (65)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (5)
- Boston University Digital Common (7)
- Brock University, Canada (16)
- Bucknell University Digital Commons - Pensilvania - USA (1)
- CaltechTHESIS (11)
- Cambridge University Engineering Department Publications Database (32)
- CentAUR: Central Archive University of Reading - UK (5)
- Center for Jewish History Digital Collections (5)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (66)
- Cochin University of Science & Technology (CUSAT), India (5)
- CORA - Cork Open Research Archive - University College Cork - Ireland (5)
- Deakin Research Online - Australia (22)
- Digital Archives@Colby (1)
- Digital Commons at Florida International University (3)
- DigitalCommons@University of Nebraska - Lincoln (1)
- Diposit Digital de la UB - Universidade de Barcelona (2)
- Doria (National Library of Finland DSpace Services) - National Library of Finland, Finland (1)
- DRUM (Digital Repository at the University of Maryland) (3)
- Duke University (2)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (22)
- Greenwich Academic Literature Archive - UK (6)
- Helda - Digital Repository of University of Helsinki (32)
- Indian Institute of Science - Bangalore - Índia (66)
- Instituto Politécnico do Porto, Portugal (14)
- Massachusetts Institute of Technology (3)
- Ministerio de Cultura, Spain (1)
- National Center for Biotechnology Information - NCBI (2)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (15)
- Portal de Revistas Científicas Complutenses - Espanha (1)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (115)
- Queensland University of Technology - ePrints Archive (181)
- Repositório Científico da Universidade de Évora - Portugal (1)
- Repositório Científico do Instituto Politécnico de Lisboa - Portugal (7)
- Repositório Institucional da Universidade de Aveiro - Portugal (14)
- Repositório Institucional da Universidade Estadual de São Paulo - UNESP (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (3)
- Research Open Access Repository of the University of East London. (3)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (3)
- SAPIENTIA - Universidade do Algarve - Portugal (4)
- South Carolina State Documents Depository (2)
- Universidad del Rosario, Colombia (19)
- Universidad Politécnica de Madrid (2)
- Universidade de Lisboa - Repositório Aberto (7)
- Universidade dos Açores - Portugal (1)
- Universitat de Girona, Spain (1)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (12)
- Université de Lausanne, Switzerland (17)
- Université de Montréal, Canada (63)
- University of Michigan (15)
- University of Queensland eSpace - Australia (7)
- University of Southampton, United Kingdom (1)
- University of Washington (2)
- WestminsterResearch - UK (5)
Resumo:
This paper proposes a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, when using RL, has been to apply value function based algorithms, the system here detailed is characterized by the use of direct policy search methods. Rather than approximating a value function, these methodologies approximate a policy using an independent function approximator with its own parameters, trying to maximize the future expected reward. The policy based algorithm presented in this paper is used for learning the internal state/action mapping of a behavior. In this preliminary work, we demonstrate its feasibility with simulated experiments using the underwater robot GARBI in a target reaching task