Incremental topological reinforcement learning agent in non-structured environments

This paper describes a new reinforcement learning (RL) model, the incremental topological reinforcement learning agent (ITRLA), designed to guide agent navigation in non-structured environments, considering two common situations: (i) insertion of noise during state estimation and (ii) changes in env...

Full description

Saved in:
Bibliographic Details
Main Authors: de S Braga, A.P., Araujo, A.F.R., Wyatt, J.
Format: Conference Proceeding
Language:English
Subjects:
Acceleration
Applied sciences
Computer science
Computer science
control theory
systems
Control theory. Systems
Equations
Exact sciences and technology
Learning
Modelling and identification
Navigation
Robots
State estimation
Stochastic resonance
Testing
Working environment noise
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes a new reinforcement learning (RL) model, the incremental topological reinforcement learning agent (ITRLA), designed to guide agent navigation in non-structured environments, considering two common situations: (i) insertion of noise during state estimation and (ii) changes in environment structure. Tasks in non-structured environments are hard to be learned by traditional RL algorithms due to the stochastic state transitions. Such tasks are often modeled as partially observable Markov decision processes (POMDP), an expensive computational process. The main contribution of the ITRLA is to handle the two mentioned situations in non-structured environments with a reduced number of trials, and avoiding POMDP modeling.
ISSN:1062-922X
2577-1655
DOI:10.1109/ICSMC.2004.1401080