Solving multiagent markov decision processes: A forest management example

MODSIM05 - International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, Proceedings

Volumn , Issue , 2005, Pages 1594-1600

  Chadès, Iadine ^a   Bouteiller, Bertrand ^a  

^a Unite de Biometrie et Intelligence Artificielle   (France)

Author keywords

Multiagent reinforcement learning; Multiagent systems; Stochastic dynamic programming

Indexed keywords

COMPLEXITY LEVELS; DESIGNING AGENTS; FINITE NUMBER; FIXED COST; GLOBAL PROBLEMS; LEARNING METHODS; MARKOV DECISION PROBLEM; MARKOV DECISION PROCESSES; MEMORY SPACE; MULTI-AGENT REINFORCEMENT LEARNING; MULTI-STAND; MULTIAGENT REINFORCEMENT LEARNING ALGORITHM; NEAR-OPTIMAL POLICIES; NEAR-OPTIMAL SOLUTIONS; OPTIMAL DECISION MAKING; OPTIMAL POLICIES; OPTIMAL SOLUTIONS; OPTIMAL STRATEGIES; PLANNING ALGORITHMS; PLANNING METHOD; REINFORCEMENT LEARNING TECHNIQUES; REWARD FUNCTION; SCHNEIDER; SEQUENTIAL DECISION MAKING; SIMULATION TECHNIQUE; SMALL SIZE; STOCHASTIC DYNAMIC PROGRAMMING; SUB-PROBLEMS; MULTI-AGENT MARKOV DECISION PROCESS;

CONVERGENCE OF NUMERICAL METHODS; COST ACCOUNTING; DECISION MAKING; DYNAMIC PROGRAMMING; FORESTRY; LEARNING ALGORITHMS; MARKOV PROCESSES; MULTI AGENT SYSTEMS; OPTIMAL SYSTEMS; OPTIMIZATION; PLANT EXTRACTS; REINFORCEMENT; REINFORCEMENT LEARNING; BEHAVIORAL RESEARCH; LEARNING SYSTEMS;

PROBLEM SOLVING; LEARNING ALGORITHMS;

EID: 80053116521     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. Bernstein, D. S., Zilberstein, S. & Immerman, N. (2000), The complexity of decentralized control of markov decision processes, in 'Proc. of UAI'.
2. Chadès, I. (2003), Planification distribuée dans les SMA l'aide de processus décisionnels deMarkov, PhD thesis, Universite Nancy 1, LORIA.
3. Chadès, I. (2004), Multiple equilibria solution for the multi-agent mdp coordination problem, in 'Workshop of Multi-Agent Markov Decision Processes: Theories and Models, ECAI04'.
4. Chadès, I., Scherrer, B. & Charpillet, F. (2002), A heuristic approach for solving decentralized-pomdp: Assessment on the pursuit problem, in 'the 2002 ACM Symposium on Applied Computing'.
5. Dutech, A., Buffet, O. & Charpillet, F. (2001), Multiagent systems by incremental gradient reinforcement learning, in 'Proceedings of IJCAI'01'.
6. Garcia, F. & Sabbadin, R. (2001), Solving large weakly coupled markov decision processes: Application to forest management, in 'MODSIM 2001'.
7. Nair, R., Tambe, M., Yokoo, M., Pynadath, D. & Marsella, S. (2003), Taming decentralized pomdps: Towards efficient policy computation for multiagent settings, in 'IJCAI'03'.
8. Puterman, M. L. (1994), Markov Decision Processes-Discrete Stochastic Dynamic Programming, John Wiley and Sons, Inc., New York, USA.
9. Schneider, J., Wong, W.-K., Moore, A. & Riedmiller, M. (1999), Distributed value functions, in 'Proc. ICML 99', Morgan Kaufmann, San Francisco, CA, pp. 371-378.
10. Shen, J., Lesser, V. & Carver, N. (2003), Minimizing communication cost in a distributed bayesian network using a decentralized mdp, in 'the second international joint conference on Autonomous agents and multiagent systems', pp. 678-685.
11. Shoham, Y., Powers, R. & Grenager, T. (2003), Multiagent reinforcement learning: a critical survey, Technical report, Stanford University.
12. Sutton, R. & Barto, G. (1998), Reinforcement Learning: an introduction, Bradford Book, MIT Press, Cambridge, MA.
13. Watkins, C. & Dayan, P. (1992), 'Q-learning', Machine Learning 8, 279-292.