Free-energy-based reinforcement learning in a partially observable environment

Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010

Volumn , Issue , 2010, Pages 541-546

  Otsuka, Makoto ^a,b   Yoshimoto, Junichiro ^a,b   Doya, Kenji ^a,b  

^a OKINAWA INSTITUTE OF SCIENCE AND TECHNOLOGY GRADUATE UNIVERSITY   (Japan)

^b NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ACTIVATION PATTERNS; EQUILIBRIUM FREE ENERGY; FUTURE OBSERVATIONS; HIGH-DIMENSIONAL; MARKOV DECISION PROCESSES; PARTIALLY OBSERVABLE ENVIRONMENTS; RESTRICTED BOLTZMANN MACHINE; VALUE FUNCTIONS;

ARTIFICIAL INTELLIGENCE; LEARNING ALGORITHMS; MARKOV PROCESSES; RECURRENT NEURAL NETWORKS; REINFORCEMENT LEARNING;

FREE ENERGY;

EID: 84887013392     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. J. Hoey and P. Poupart. Solving POMDPs with continuous or large discrete observation spaces. In IJCAI, volume 19, page 1332, 2005.
2. M. Toussaint, L. Charlin, and P. Poupart. Hierarchical POMDP controller optimization by likelihood maximization. UAI, 2008.
3. B. Sallans and G. E. Hinton. Reinforcement learning with factored states and actions. Journal of Machine Learning Research, 5:1063-1088, 2004.
4. S. D. Whitehead and L. J. Lin. Reinforcement learning of non-Markov decision processes. Artificial Intelligence, 73:271-306, 1995.
5. R. S. Sutton and A. G. Barto. Reinforcement Learning. MIT Press, 1998.
6. P. J. Werbos. Backpropagation through time: what it does and how to do it. Proceedings of the IEEE, 78(10):1550-1560, 1990.
7. B. Bakker. Reinforcement learning with long short-term memory. NIPS, 2:1475-1482, 2002.