Autonomous development of basic behaviors of an agent;Développement autonome des comportements de base d'un agent

Revue d'Intelligence Artificielle

Volumn 19, Issue 4-5, 2005, Pages 603-632

  Buffet, Olivier ^a,b   Dutech, Alain ^b   Charpillet, François ^b  

^a AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

^b LORIA   (France)

Author keywords

Markov Decision Problems; Multiple Motivations; Reinforcement Learning

Indexed keywords

DECISION THEORY; LEARNING SYSTEMS; MARKOV PROCESSES;

MARKOV DECISION PROBLEMS; MULTIPLE MOTIVATIONS; REINFORCEMENT LEARNING;

AUTONOMOUS AGENTS;

EID: 33645896149     PISSN: 0992499X     EISSN: None     Source Type: Journal    
DOI: 10.3166/ria.19.603-632     Document Type: Conference Paper

References (43)

1. Baxter J., Bartlett P., «Infinite-Horizon Policy-Gradient Estimation », Journal of Artificial Intelligence Research, vol. 15, p. 319-350, 2001a.
2. Baxter J., Bartlett P., Weaver L., «Experiments with Infinite-Horizon, Policy-Gradient Estimation », Journal of Artificial Intelligence Research, vol. 15, p. 351-381, 2001b.
3. Bertsekas D., Tsitsiklis J., Neurodynamic Programming, Athena Scientifi c, 1996.
4. Boutilier C., Reiter R., Price B., «Symbolic Dynamic Programming for First-order MDPs », Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI'01), p. 690-697, 2001.
5. Buffet O., Une double approche modulaire de l'apprentissage par renforcement pour des agents intelligents adaptatifs, PhD thesis. Université Henri Poincaré, Nancy 1, septembre, 2003. Laboratoire Lorrain de recherche en informatique et ses applications (LORIA).
6. Buffet O., Dutech A., Charpillet F., «Adaptive Combination of Behaviors in an Agent », Proceedings of the 15th European Conference on Artificial Intelligence (ECAI'02), 2002.
7. Buffet O., Dutech A., Charpillet F., «Automatic Generation of an Agent's Basic Behaviors », Proceedings of the 2nd International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'03), 2003.
8. Cassandra A. R., Exact and Approximate Algorithms for Partially Observable Markov Decision Processes, PhD thesis, Brown University, Department of Computer Science, Providence, RI, 1998.
9. Dayan P., Hinton G., «Feudal Reinforcement Learning », Advances in Neural Information Processing Systems 5 (NIPS'93), 1993.
10. Dietterich T., «Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition », Journal of Artificial Intelligence Research, vol. 13, p. 227-303, 2000.
11. Digney B., «Learning Hierarchical Control Structure for Multiple Tasks and Changing Environments », Proceedings of the Fifth Conference on the Simulation of Adaptive Behavior (SAB'98), 1998.
12. Dutech A., Buffet O., Charpillet E, «Multi-Agent Systems by Incremental Gradient Reinforcement Learning », Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI'01), 2001.
13. Dzeroski S., Raedt L. D., Driessens K., «Relational reinforcement learning », Machine Learning, vol. 43, p. 7-52, 2001.
14. Genest C, Zidek J., «Combining Probability Distributions : A Critique and an Annotated Bibliography », Statistical Science, vol. 1, no 1, p. 114-135, February, 1986.
15. Gretton C., Thiébaux S., «Exploiting First-Order Regression in Inductive Policy Selection », Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence (UAI'04), 2004.
16. Hauskretch M., Meuleau N., Kaelbling L., Dean T., Boutilier C., «Hierarchical Solution of Markov Decision Processes Using Macro-Actions », Proceedings of the Fourteenth International Conference on Uncertainty in Artificial Intelligence (UAI'98), p. 220-229, 1998.
17. Hengst B., «Discovering Hierarchy in Reinforcement Learning with HEXQ », Proceedings of the Nineteenth International Conference on Machine Learning (ICML'02), p. 243-250, 2002.
18. Humphrys M., «Action Selection methods using Reinforcement Learning », From Animals to Animals 4 : 4th International Conference on Simulation of Adaptive Behavior (SAB-96), September, 1996.
19. Jaakkola T., Jordan M., Singh S., «On the Convergence of Stochastic Iterative Dynamic Programming Algorithms », Neural Computation, vol. 6, no 6, p. 1186-1201, 1994.
20. Jennings N., Sycara K., Wooldridge M., «A Roadmap of Agent Research and Development », Autonomous Agents and Multi-Agent Systems, vol. 1, p. 7-38, 1998.
21. Joslin D., Nunes A., Pollack M. E., TileWorld Users' Manual, Technical Report no TR 93-12, August, 1993.
22. Kaelbling L., «Hierarchical Learning in Stochastic Domains : Preliminary Results », Proceedings of the Tenth International Conference on Machine Learning (ICML'93), 1993.
23. Kaelbling L., Littman M., Moore A., «Reinforcement Learning : A Survey », Journal of Artificial Intelligence Research, vol. 4, p. 237-285, 1996.
24. Kearns M., Mansour Y., Ng A., «A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes », Machine Learning, vol. 49, p. 193-208, 2002.
25. Lin. L.-J., «Self-improving reactive agent based on reinforcement learning, planning and teaching. », Machine Learning, vol. 8, p. 293-321, 1992.
26. Lin L.-J., «Hierarchical Learning of Robot Skills », Proceedings of the IEEE International Conference on Neural Networks (ICNN'93), 1993.
27. Littman M., Cassandra A., Kaelbling L., «Learning policies for partially observable environments : scaling up », Proceedings of the 12th International Conference on Machine Learning (ICML'95), 1995.
28. MacKay D., Information Theory, Inference, and Learning Algorithms, Cambridge University Press, 2003.
29. Mahadevan S., Cornell J., «Automatic Programming of Behavior-based Robots using Reinforcement Learning », Artificial Intelligence, vol. 55, no 2-3, p. 311-365, June, 1992.
30. McCallum R. A., Reinforcement Learning with Selective Perception and Hidden State, PhD thesis, University of Rochester, 1995.
31. Nehmzow U., Smithers T., McGonigle B., «Increasing Behavioural Repertoire in a Mobile Robot », From Animals to Animats : Proceedings of the Second Conference on the Simulation of Adaptive Behavior (SAB'93), 1993.
32. Parr R. E., Hierarchical Control and Learning for Markov Decision Processes, PhD thesis, 1998.
33. Peret L., Garcia F., «On-line search for solving Markov Decision Processes via heuristic sampling », Proceedings of the 16th European Conference on Artificial Intelligence (ECAI'2004), 2004.
34. Piaget J., La Psychologie de l'Intelligence, Armand Colin, 1967.
35. Puterman M. L., Markov Decision Processes-Discrete Stochastic Dynamic Programming, John Wiley and Sons, Inc., New York, USA, 1994.
36. Russell S., Norvig P., Artificial Intelligence : A Modern Approach, Englewood Cliffs, NJ : prentice Hall, 1995.
37. Shoham Y., Powers R., Grenager T., Multi-agent reinforcement learning : a critical survey. Technical report, Stanford, 2003.
38. Singh S., Jaakkola T., Jordan M., «Learning without state estimation in Partially Observable Markovian Decision Processes », Proceedings of the Eleventh International Conference on Machine Learning (ICML'94), 1994.
39. Sutton R., Barto G., Reinforcement Learning : an introduction, Bradford Book, MIT Press, Cambridge, MA, 1998.
40. Tyrrell T., Computational Mechanisms for Action Selection, PhD thesis, University of Edinburgh, 1993.
41. Urzelai J., Floreano D., Dorigo M., Colombetti M., «Incremental Robot Shaping », Connection Science Journal, 1998.
42. Watkins C., Learning from delayed rewards, PhD thesis, King's College of Cambridge, UK., 1989.
43. Weng J., «A Theory of Mentally Developing Robots », Proceedings of the 2nd International Conference on Development and Learning (ICDL'02), June, 2002.