Use este identificador para citar ou linkar para este item:
Título: A topological reinforcement learning agent for navigation
Autor(es): Braga, Arthur Plínio de Souza
Araújo, Aluízio F. R.
Palavras-chave: Aceleração da aprendizagem
Aprendizado por esfoço
Redes Neurais
Mapas topológicos
Data do documento: 9-Nov-2003
Editor: Neural Comput. & Applic.
Citação: BRAGA, A. P. S. ; ARAÚJO, A. F. R. (2003)
Abstract: This article proposes a reinforcement learning procedure for mobile robot navigation using a latentlike learning schema. Latent learning refers to learning that occurs in the absence of reinforcement signals and is not apparent until reinforcement is introduced. This concept considers that part of a task can be learned before the agent receives any indication of how to perform such a task. In the proposed topological reinforcement learning agent (TRLA), a topological map is used to perform the latent learning. The propagation of the reinforcement signal throughout the topological neighborhoods of the map permits the estimation of a value function which takes in average less trials and with less updatings per trial than six of the main temporal difference reinforcement learning algorithms: Q-learning, SARSA, Q(k)-learning, SARSA(k), Dyna-Q and fast Q(k)-learning. The RL agents were tested in four different environments designed to consider a growing level of complexity in accomplishing navigation tasks. The tests suggested that the TRLA chooses shorter trajectories (in the number of steps) and/or requires less value function updatings in each trial than the other six reinforcement learning (RL) algorithms.
Descrição: BRAGA, A. P. S. ; ARAÚJO, A. F. R. A topological reinforcement learning agent for navigation. Neural Comput. & Applic., v. 12, p. 220–236, nov. 2003.
ISSN: 003-0385-9
Aparece nas coleções:DEEL - Artigos publicados em revista científica

Arquivos associados a este item:
Arquivo Descrição TamanhoFormato 
2003_art_apsbraga.pdf781,35 kBAdobe PDFVisualizar/Abrir

Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.