File(s) under permanent embargo
Action selection methods in a robotic reinforcement learning scenario
conference contribution
posted on 2018-01-01, 00:00 authored by F Cruz Naranjo, P Wuppen, A Fazrie, C Weber, S WermterReinforcement learning allows an agent to learn a new task while autonomously exploring its environment. For this aim, the agent chooses an action to perform among the available ones for a certain state. Nonetheless, a common problem for a reinforcement learning agent is to find a proper balance between exploration and exploitation of actions in order to achieve an optimal behavior. This paper compares multiple approaches to the exploration/exploitation dilemma in reinforcement learning and, moreover, it implements an exemplary reinforcement learning task within the domain of domestic robotics to show the performance of different exploration policies on it. We perform the domestic task using -greedy, softmax, VDBE, and VDBE-Softmax with online and offline temporal-difference learning. The obtained results show that the agent is able to collect larger and faster reward by using the VDBE-Softmax exploration strategy with both Q-learning and SARSA.
History
Event
Latin American Computational Intelligence Society. Conference (2018 : Gudalajara, Mexico)Series
Latin American Computational Intelligence Society ConferencePagination
1 - 6Publisher
Institute of Electrical and Electronics EngineersLocation
Gudalajara, MexicoPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2018-11-07End date
2018-11-09ISBN-13
9781538646250Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2019, IEEEEditor/Contributor(s)
[Unknown]Title of proceedings
LA-CCI : Proceedings of the 2018 IEEE Latin American Conference on Computational IntelligenceUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC