Abstract

Reinforcement learning (RL) is a simulation-based technique useful in solving Markov decision processes if their transition probabilities are not easily obtainable or if the problems have a very large number of states. We present an empirical study of (i) the effect of step-sizes (learning rules) in the convergence of RL algorithms, (ii) stochastic shortest paths in solving average reward problems via RL, and (iii) the notion of survival probabilities (downside risk) in RL. We also study the impact of step sizes when function approximation is combined with RL. Our experiments yield some interesting insights that will be useful in practice when RL algorithms are implemented within simulators.

Department(s)

Engineering Management and Systems Engineering

Keywords and Phrases

Markov Processes; Function Approximation; Learning (Artificial Intelligence)

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type

text

Language(s)

English

Rights

© 2008 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Full Text Link

Share

 
COinS