Domain-independent optimistic initialization for reinforcement learning

AAAI Workshop - Technical Report

Volumn WS-15-10, Issue , 2015, Pages 29-31

  Machado, Marios C ^a   Srinivasan, Sriram ^a   Bowling, Michael ^a  

^a UNIVERSITY OF ALBERTA   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE;

DOMAIN INDEPENDENTS; FEATURE REPRESENTATION; FUNCTION APPROXIMATION; SIMPLE APPROACH; VALUE FUNCTIONS;

REINFORCEMENT LEARNING;

EID: 84964652743     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. Bellemare, M. G.; Naddaf, Y.; Veness, J.; and Bowling, M. 2013. The Arcade Learning Environment: An Evaluation Platform for General Agents. Journal of Artificial Intelligence Research 47:253-279.
2. Defazio, A., and Graepel, T. 2014. A comparison of learning algorithms on the arcade learning environment. Corr abs/1410.8620.
3. Rummery, G. A., and Niranjan, M. 1994. Online Q-learning using connectionist systems. CUED/F-INFENG/TR 166, Cambridge Univ. Engineering Dept.
4. Sutton, R. S., and Barto, A. G. 1998. Reinforcement Learning: An Introduction. MIT Press.