Design, analysis and comparison of robot learners

Robotics and Autonomous Systems

Volumn 24, Issue 1-2, 1998, Pages 17-32

  Wyatt, Jeremy ^a   Hoar, John ^a   Hayes, Gillian ^a  

^a NONE

Author keywords

Experimental methodology; Q learning; Reinforcement learning; Robot learning

Indexed keywords

COMPUTATIONAL COMPLEXITY; DECISION THEORY; LEARNING ALGORITHMS;

REINFORCEMENT LEARNING;

ROBOT LEARNING;

EID: 0032131047     PISSN: 09218890     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0921-8890(98)00019-0     Document Type: Article

References (20)

1. T. Balch, Social entropy: A new metric for learning multi-robot teams, in: Proceedings of 10th International Florida Artificial Intelligence Research Symposium, Florida AI Research Society, 1997, pp. 272-277.
2. A.G. Barto, Connectionist learning for control, in: W.T. Miller, R.S. Sutton, P.J. Werbos (Eds.), Neural Networks for Control, MIT Press, Cambridge, MA, 1990, pp. 5-58.
3. D. Chapman, L.P. Kaelbling, Input generalisation in delayed reinforcement learning: An algorithm and performance comparison, in: Proceedings of International Joint Conference on Artificial Intelligence (IJCAI-91), Sydney, Australia, 1991.
4. G.M. Clarke, D. Cooke, A Basic Course in Statistics, 3rd ed., Edward Arnold, Paris, 1992.
5. P.R. Cohen, Empirical Methods for Artificial Intelligence, MIT Press, Cambridge, MA, 1995.
6. Y. Faihe, J.-P. Muller, Analysis and design of a robot's behaviour: Towards a methodology, in: J. Demiris, A. Birk (Eds.), Proceedings of Sixth European Workshop on Learning Robots, 1997.
7. J. Hallam, G. Hayes, Benchmarks for mobile robotics? in: Towards Intelligent Mobile Robots: Scientific methods in mobile robotics, Manchester University, School of Computer Science, Available as Technical Report UMCS-97-9-1, 1997.
8. H. Hexmoor, Robolearn 97: An international workshop on evaluating robot learning, Technical Report TR 97-03, Department of Computer Science, State University of New York at Buffalo, April 1997.
9. J. Hoar, Reinforcement learning applied to a real robot task, Unpublished Masters Thesis, University of Edinburgh, Department of Artificial Intelligence, September 1996.
10. L.P. Kaelbling, Learning in embedded systems, Ph.D. Thesis, Department of Computer Science, Stanford, 1990.
11. S. Mahadevan, J.H. Connell, Automatic programming of behaviour-based robots using reinforcement learning, Research Report RC 16359 (72625), IBM Research Division, July 1990.
12. M. Mataric, Evaluation of learning performance of situated embodied agents, in: Proceedings of the Third European Conference on Artificial Life, Morgan Kaufmann, Los Altos, CA, 1995, pp. 579-589.
13. J. Peng, R.J. Williams, Incremental multi-step Q-learning, in: W.W. Cohen, H. Hirsh (Eds.), Machine Learning: Proceedings of the 11th International Conference, 1994, pp. 226-232.
14. S. Singh, R. Sutton, Reinforcement learning with replacing eligibility traces, Machine Learning 22 (1996) 123-158.
15. R.S. Sutton, Temporal credit assignment in reinforcement learning, Ph.D. Thesis, University of Massachusetts, School of Computer and Information Sciences, 1984.
16. R.S. Sutton, A.G. Barto, Reinforcement Learning: An Introduction, MIT Press/Bradford Books, Cambridge, MA, 1998.
17. C.J.C.H. Watkins, Learning from delayed rewards, Thesis, University of Cambridge, King's College, Cambridge, UK, May 1989.
18. S.D. Whitehead, D. Ballard, Learning to perceive and act, Technical Report TR-331 (revised), Department of Computer Science, University of Rochester, June 1990.
19. S. Whitehead, L.-J. Lin, Reinforcement learning in non-Markov decision processes, Artificial Intelligence 73 (1995) 271-306.
20. J. Wyatt, G. Hayes, J. Hallam, Investigating the behaviour of Q(λ), Technical Report 783, Department of Artificial Intelligence, Edinburgh University, January 1996, Presented at the IEE Colloquia on Self Learning Robots, February 12, 1996, London.