Exploration bonuses and dual control

Machine Learning

Volumn 25, Issue 1, 1996, Pages 5-22

  Dayan, Peter ^a   Sejnowski, Terrence J ^b,c  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^b HOWARD HUGHES MEDICAL INSTITUTE   (United States)

^c UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Certainty equivalence; Dynamic programming; Exploration bonuses; Non stationary environment; Reinforcement learning

Indexed keywords

ADAPTIVE CONTROL SYSTEMS; DYNAMIC PROGRAMMING; MATHEMATICAL MODELS; OPTIMAL CONTROL SYSTEMS; PARAMETER ESTIMATION; PROBABILITY; STATISTICAL METHODS;

EXPLORATION BONUSES; NONSTATIONARY ENVIRONMENT; REINFORCEMENT LEARNING;

LEARNING SYSTEMS;

EID: 0030260201     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1007/bf00115298     Document Type: Article

References (4)

1. Barto, A.G., Bradtke, S.J. & Singh, S.P. (1995). Learning to act using real-time dynamic programming. Artificial Intelligence, 72, 81-138.
2. Lovejoy, W.S. (1991). A survey of algorithmic methods for partially observed Markov decision processes. Annals of Operations Research, 28, 47-66.
3. Monahan, G.E. (1982). A survey of partially observable Markov decision processes: Theory, models and algorithms. Management Science, 28, 1-16.
4. Moore, A.W. & Atkeson, C.G. (1993). Prioritized sweeping: Reinforcement learning with less data and less real time. Machine Learning, 13, 103-130.