A compact, hierarchically optimal Q-function decomposition

Proceedings of the 22nd Conference on Uncertainty in Artificial Intelligence, UAI 2006

Volumn , Issue , 2006, Pages 332-340

  Marthi, Bhaskara ^a   Russell, Stuart ^a   Andre, David ^b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b BodyMedia Inc   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPLEX ENVIRONMENTS; CONCISE REPRESENTATIONS; HIERARCHICAL REINFORCEMENT LEARNING; NONLOCAL; Q-FUNCTIONS; RUNTIME ARCHITECTURE; STATE ABSTRACTION; STATE DISTRIBUTIONS; STRUCTURAL CONDITION; VALUE FUNCTIONS;

REINFORCEMENT LEARNING;

ARTIFICIAL INTELLIGENCE;

EID: 80053178447     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. D. Andre and S. Russell. State abstraction for programmable reinforcement learning agents. In AAAI, 2002.
2. D. Andre. Programmable Reinforcement Learning Agents. PhD thesis, UC Berkeley, 2003.
3. C. Boutilier, T. Dean, and S. Hanks. Decision theoretic planning: structural assumptions and computational leverage. Journal of Artificial Intelligence Research, 11:1-94, 1999. (Pubitemid 129628760)
4. T. Dean and S.-H. Lin. Decomposition techniques for planning in stochastic domains. In IJCAI, 1995.
5. T. Dietterich. Hierarchical reinforcement learning with the maxq value function decomposition. JAIR, 13:227-303, 2000. (Pubitemid 33682087)
6. M. Hauskrecht, N. Meuleau, C. Boutilier, L. Kaelbling, and T. Dean. Hierarchical solution of Markov decision processes using macro-actions. In UAI, 1998.
7. N. Meuleau, R. Brafman, and E. Benaz-era. Stochastic over-subscription planning using hierarchies of MDPs. In ICAPS, 2006.
8. R. Parr and S. Russell. Reinforcement learning with hierarchies of machines. In NIPS, 1997.
9. R. Parr. Flexible decomposition algorithms for weakly coupled Markov decision processes. In UAI, 1998.
10. D. Precup and R. Sutton. Multi-time models for temporally abstract planning. In NIPS, 1998.