Journal
SOFT COMPUTING
Volume 17, Issue 11, Pages 2101-2108Publisher
SPRINGER
DOI: 10.1007/s00500-013-1112-9
Keywords
Goal representation heuristic dynamic programming (GrHDP); Maze navigation/path planning; Adaptive dynamic programming (ADP); Reinforcement learning (RL)
Categories
Funding
- National Science Foundation (NSF) [CAREER ECCS 1053717]
- Army Research Office (ARO) [W911NF-12-1-0378]
- NSF-DFG Collaborative Research on Autonomous Learning [CNS 1117314]
- Directorate For Engineering
- Div Of Electrical, Commun & Cyber Sys [1053717] Funding Source: National Science Foundation
- Division Of Computer and Network Systems
- Direct For Computer & Info Scie & Enginr [1117314] Funding Source: National Science Foundation
Ask authors/readers for more resources
In this paper, we analyze an internal goal structure based on heuristic dynamic programming, named GrHDP, to tackle the 2-D maze navigation problem. Classical reinforcement learning approaches have been introduced to solve this problem in literature, yet no intermediate reward has been assigned before reaching the final goal. In this paper, we integrated one additional network, namely goal network, into the traditional heuristic dynamic programming (HDP) design to provide the internal reward/goal representation. The architecture of our proposed approach is presented, followed by the simulation of 2-D maze navigation (10*10) problem. For fair comparison, we conduct the same simulation environment settings for the traditional HDP approach. Simulation results show that our proposed GrHDP can obtain faster convergent speed with respect to the sum of square error, and also achieve lower error eventually.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available