Optimal rewards versus leaf-evaluation heuristics in planning agents

Proceedings of the National Conference on Artificial Intelligence

Volumn 1, Issue , 2011, Pages 465-470

  Sorg, Jonathan ^a   Singh, Satinder ^a   Lewis, Richard L ^a  

^a UNIVERSITY OF MICHIGAN   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AGENT DESIGN; ALTERNATIVE APPROACH; COMPUTATIONAL CONSTRAINTS; COMPUTATIONAL RESOURCES; DESIGN APPROACHES; EVALUATION FUNCTION; HEURISTIC APPROACH; OPTIMAL REWARD; PLANNING AGENTS; REWARD FUNCTION; SPARSE SAMPLING; STATE SPACE;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; DESIGN; HEURISTIC METHODS; PLANT EXTRACTS; TREES (MATHEMATICS);

FUNCTION EVALUATION;

EID: 80055052859     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Asmuth, J.; Littman, M. L.; and Zinkov, R. 2008. Potential-based shaping in model-based reinforcement learning. In Proceedings of the 23rd AAAI, 604-609. AAAI Press.
2. Bartlett, P. L., and Baxter, J. 2000. Stochastic optimization of controlled partially observable Markov decision processes. In Proceedings of the 39th IEEE Conference on Decision and Control.
3. Finnsson, H., and Björnsson, Y. 2008. Simulation-based approach to general game playing. In Proceedings of the 23rd AAAI, 259-264.
4. Gelly, S., and Silver, D. 2008. Achieving master level play in 9 x 9 computer Go. Proceedings of the 23rd AAAI.
5. Kearns, M.; Mansour, Y.; and Ng, A. Y. 1999. A sparse sampling algorithm for near-optimal planning in large Markov decision processes. In Proceedings of the 16th IJCAI, 1324-1331.
6. Kocsis, L., and Szepesvári, C. 2006. Bandit based Monte-Carlo planning. In Proceedings of the 17th ECML, 282-293.
7. Neu, G., and Szepesvári, C. 2007. Apprenticeship learning using inverse reinforcement learning and gradient methods. In Proceedings of the 23rd UAI, 295-302.
8. Ng, A. Y.; Russell, S. J.; and Harada, D. 1999. Policy invariance under reward transformations: theory and application to reward shaping. In Proceedings of the 16th ICML, 278-287.
9. Shannon, C. E. 1950. Programming a computer for playing chess. In Philosophical Magazine Vol. 41, 256-275.
10. Sorg, J.; Singh, S.; and Lewis, R. L. 2010a. Gradient methods for internal reward optimization. In Advances in NIPS 23.
11. Sorg, J.; Singh, S.; and Lewis, R. L. 2010b. Internal rewards mitigate agent boundedness. In Proceedings of the 27th ICML.