Multi-task evolutionary shaping without pre-specified representations

Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10

Volumn , Issue , 2010, Pages 1039-1046

  Snel, Matthijs ^a   Whiteson, Shimon ^a  

^a UNIVERSITY OF AMSTERDAM   (Netherlands)

Author keywords

Feature selection; Genetic algorithms; Reinforcement learning; Shaping

Indexed keywords

ALTERNATIVE METHODS; COMPUTATIONAL COSTS; FEATURE SELECTION; FEATURE SELECTION METHODS; FITNESS MEASURES; SHAPING; SPEED-UPS; VALUE FUNCTIONS;

FEATURE EXTRACTION; GENETIC ALGORITHMS; REINFORCEMENT LEARNING;

LEARNING ALGORITHMS;

EID: 77955914197     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/1830483.1830671     Document Type: Conference Paper

References (20)

1. M. Dorigo andM. Colombetti. Robot shaping: developing autonomous agents through learning. Artificial Intelligence, 71(2): 321-370, 1994.
2. S. Elfwing, E. Uchibe, K. Doya, andH. Christensen. Co-evolution of shaping: Rewards and metaparameters in reinforcement learning. Adaptive Behavior, 16(6): 400-412, 2008.
3. K. Ferguson andS. Mahadevan. Proto-transfer learning in mar kov decision processes using spectral methods. In ICML Workshop on Structural Knowledge Transfer for Machine Learning, 2006.
4. M. Grzes andD. Kudenko. Learning shaping rewards in model-based reinforcement learning. In Proc. AAMAS 2009 Workshop on Adaptive Learning Agents, 2009.
5. D. Koller andM. Sahami. Toward optimal feature selection. In Proc. 13th International Conference on Machine Learning, pages 284-292, 1996.
6. G. Konidaris andA. Barto. Autonomous shaping: Knowledge transfer in reinforcement learning. In Proc. 23rd Int. Conference on Machine Learning, pages 489-496, 2006.
7. S. Kullback andR. Leibler. On information and sufficiency. Annals of Math. Statistics, 22: 76-86, 1951.
8. A. Laud andG. DeJong. Reinforcement learning and shaping: Encouraging intended behaviors. In Proc. 19th Int. Conference on Machine Learning, pages 355-362, 2002.
9. A. Lazaric. Knowledge Transfer in Reinforcement Learning. PhD thesis, Politecnico di Milano, 2008.
10. B. Marthi. Automatic shaping and decomposition of reward functions. In Proc. 24th International Conference on Machine Learning, pages 601-608, 2007.
11. M. J. Matarić. Reward functions for accelerated learning. In Proc. 11th Int. Conference on Machine Learning, 1994.
12. A. Ng, D. Harada, andS. Russell. Policy invariance under reward transformations: Theory and application to reward shaping. In Proc. 16th International Conference on Machine Learning, 1999.
13. R. Parr, L. Li, G. Taylor, C. Painter-Wakefield, andM. Littman. An analysis of linear models, linear valuefunction approximation, and feature selection for reinforcement learning. In Proc. 25th International Conference on Machine Learning, pages 752-759, 2008.
14. J. Randløv andP. Alstrøm. Learning to drive a bicycle using reinforcement learning and shaping. In Proc. 15th International Conference on Machine Learning, 1998.
15. S. Singh, R. Lewis, andA. Barto. Where do rewards come from? In Proc. 31st Annual Conference of the Cognitive Science Society, pages 2601-2606, 2009.
16. M. Snel andG. Hayes. Evolution of valence systems in an unstable environment. In Proc. 10th Int. Conference on Simulation of Adaptive Behavior, pages 12-21, 2008.
17. M. Taylor andP. Stone. Transfer learning for reinforcement learning domains: A survey. Journal of Machine Learning Research, 10(1): 1633-1685, 2009.
18. C. J. C. H. Watkins andP. Dayan. Q-learning. Machine Learning, 8: 279-292, 1992.
19. E. Wiewiora. Potential-based shaping and q-value initialization are equivalent. Journal of Artificial Intelligence Research, 19: 205-208, 2003.
20. E. Wiewiora, G. Cottrell, andC. Elkan. Principled methods for advising reinforcement learning agents. In Proc. 20th International Conference on Machine Learning, pages 792-799, 2003.