Multi-agent Q-learning and regression trees for automated pricing decisions

Proceedings - 4th International Conference on MultiAgent Systems, ICMAS 2000

Volumn , Issue , 2000, Pages 447-448

  Sridharan, M ^a   Tesauro, G ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; APPROXIMATION ALGORITHMS; FORESTRY; LEARNING ALGORITHMS; REINFORCEMENT LEARNING; SOFTWARE AGENTS; TABLE LOOKUP; TREES (MATHEMATICS);

COMPETITIVE MARKETPLACE; FUNCTION APPROXIMATION; LEARNING PROCEDURES; MULTI-AGENT Q-LEARNING; NON-STATIONARY ENVIRONMENT; OPTIMAL POLICIES; STATIONARY ENVIRONMENTS; THEORETICAL GUARANTEES;

MULTI AGENT SYSTEMS;

EID: 84962045565     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICMAS.2000.858518     Document Type: Conference Paper

References (4)

1. C. J. C. H. Watkins, "Learning from delayed rewards." Ph. D. thesis, Cambridge University, 1989.
2. Descriptions and prior studies of these economic models are available on the Web at: http://www.research.ibm.com/infoecon/researchpapers.html.
3. G. Tesauro and J. O. Kephart,"Pricing in agent economies using multi-agent Q-learning." Proceedings of: Workshop on Decision Theoretic and Game Theoretic Agents, London, England, 5-6 July 1999.
4. X. Wang and T. G. Dietterich, "Efficient value function approximation using regression trees." Proceedings of: IJCAI-99 Workshop on Statistical Machine Learning for Large-Scale Optimization, Stockholm, Sweden, 31 Jul. 1999.