| Full text | |
| Author(s): |
Ferreira, Leonardo A.
[1]
;
Bianchi, Reinaldo A. C.
[2]
;
Santos, Paulo E.
[2]
;
Lopez de Mantaras, Ramon
[3]
Total Authors: 4
|
| Affiliation: | [1] Univ Metodista Sao Paulo, Rua Alfeu Tavares 149, Sao Paulo - Brazil
[2] Ctr Univ FEI, Av Humberto Alencar Castelo Branco 3972, Sao Paulo - Brazil
[3] Inst Invest Intelligencia Artificial, Bellaterra 08193, Catalonia - Spain
Total Affiliations: 3
|
| Document type: | Journal article |
| Source: | APPLIED INTELLIGENCE; v. 47, n. 4, p. 993-1007, DEC 2017. |
| Web of Science Citations: | 1 |
| Abstract | |
Non-stationary domains, where unforeseen changes happen, present a challenge for agents to find an optimal policy for a sequential decision making problem. This work investigates a solution to this problem that combines Markov Decision Processes (MDP) and Reinforcement Learning (RL) with Answer Set Programming (ASP) in a method we call ASP(RL). In this method, Answer Set Programming is used to find the possible trajectories of an MDP, from where Reinforcement Learning is applied to learn the optimal policy of the problem. Results show that ASP(RL) is capable of efficiently finding the optimal solution of an MDP representing non-stationary domains. (AU) | |
| FAPESP's process: | 11/19280-8 - CogBot: integrating perceptual information and semantic knowledge in cognitive robotics |
| Grantee: | Anna Helena Reali Costa |
| Support Opportunities: | Regular Research Grants |
| FAPESP's process: | 16/18792-9 - Describing, representing and solving spatial puzzles |
| Grantee: | Paulo Eduardo Santos |
| Support Opportunities: | Research Grants - Research Partnership for Technological Innovation - PITE |
| FAPESP's process: | 16/21047-3 - ALIS: Autonomous Learning in Intelligent System |
| Grantee: | Anna Helena Reali Costa |
| Support Opportunities: | Regular Research Grants |