Learning Model-free robot control by a Monte Carlo em algorithm

Autonomous Robots

Volumn 27, Issue 2, 2009, Pages 123-130

  Vlassis, Nikos ^a   Toussaint, Marc ^b   Kontes, Georgios ^a   Piperidis, Savas ^a  

^a TECHNICAL UNIVERSITY OF CRETE   (Greece)

^b TECHNISCHE UNIVERSITÄT BERLIN   (Germany)

Author keywords

EM algorithm; Model free robot control; Probabilistic inference; Reinforcement learning

Indexed keywords

CONTROLLER PARAMETER; EM ALGORITHM; GEOMETRIC DISTRIBUTION; INFINITE HORIZONS; LEARNING MODELS; MODEL FREE; MODEL-FREE ROBOT CONTROL; MONTE CARLO EM ALGORITHM; MONTREAL , CANADA; NEURAL INFORMATION PROCESSING SYSTEMS; ON-MACHINES; PROBABILISTIC INFERENCE; PROBABILISTIC MODELS; REAL ROBOT; ROBOT CONTROLS; ROBOT TRAJECTORY;

DATA PROCESSING; EDUCATION; INFERENCE ENGINES; LIGHT MEASUREMENT; MATHEMATICAL MODELS; MONTE CARLO METHODS; REINFORCEMENT; REINFORCEMENT LEARNING; ROBOT LEARNING; ROBOTS;

LEARNING ALGORITHMS;

EID: 70349327392     PISSN: 09295593     EISSN: None     Source Type: Journal    
DOI: 10.1007/s10514-009-9132-0     Document Type: Article

References (21)

1. Abbeel, P., Coates, A., Quigley, M., & Ng, A. Y. (2007). An application of reinforcement learning to aerobatic helicopter flight. In Proc. neural information processing systems.
2. Bertsekas, D. P., & Tsitsiklis, J. N. (1996). Neuro-dynamic programming. Nashua: Athena Scientific.
3. Cooper, G. F. (1988). A method for using belief networks as influence diagrams. In Proc. 4th workshop on uncertainty in artificial intelligence (pp. 55-63), Minneapolis, Minnesota.
4. P. Dayan G. E. Hinton 1997 Using expectation-maximization for reinforcement learning Neural Computation 9 2 271 278 0876.68090 10.1162/neco.1997.9.2.271
5. A. P. Dempster N. M. Laird D. B. Rubin 1977 Maximum likelihood from incomplete data via the EM algorithm Journal of the Royal Statistical Society Series B 39 1 38 0364.62022 501537
6. Hoffman, M., Doucet, A., de Freitas, N., & Jasra, A. (2008). Bayesian policy learning with trans-dimensional MCMC. In Proc. neural information processing systems.
7. Y. Kim S. H. Kim Y. K. Kwak 2005 Dynamic analysis of a nonholonomic two-wheeled inverted pendulum robot Journal of Intelligent and Robotic Systems 44 1 25 46 10.1007/s10846-005-9022-4
8. Kober, J., & Peters, J. (2009). Policy search for motor primitives in robotics. In Proc. neural information processing systems.
9. Martinez-Cantin, R., de Freitas, N., Castellanos, J. A., & Doucet, A. (2009). A Bayesian exploration-exploitation approach for optimal online sensing and planning with a visually guided mobile robot. Autonomous Robots. doi: 10.1007/s10514-009-9130-2.
10. Neal, R. M., & Hinton, G. E. (1998). A view of the EM algorithm that justifies incremental, sparse, and other variants. In M. I. Jordan (Ed.), Learning in graphical models (pp. 355-368). Dordrecht: Kluwer Academic.
11. Ng, A. Y., & Jordan, M. I. (2000). PEGASUS: a policy search method for large MDPs and POMDPs. In Proc. uncertainty in artificial intelligence.
12. J. Peters S. Schaal 2008 Natural actor critic Neurocomputing 71 7-9 1180 1190 10.1016/j.neucom.2007.11.026
13. J. Peters S. Schaal 2008 Reinforcement learning of motor skills with policy gradients Neural Networks 21 4 682 697 10.1016/j.neunet.2008.02.003
14. Peters, J., & Kober, J. (2009). Using reward-weighted imitation for robot reinforcement learning. In Proc. 2009 IEEE int. symp. on approximate dynamic programming and reinforcement learning.
15. M. Riedmiller T. Gabel R. Hafner S. Lange 2009 Reinforcement learning for robot soccer Autonomous Robots 27 1 55 73 10.1007/s10514-009-9120-4 This issue, part A
16. Rückstie, T., Felder, M., & Schmidhuber, J. (2008). State-dependent exploration for policy gradient methods. In Proc. European conf. on machine learning.
17. Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: an introduction. Cambridge: MIT Press.
18. Tedrake, R., Zhang, T. W., & Seung, H. S. (2005). Learning to walk in 20 minutes. In Proc. 14th Yale workshop on adaptive and learning systems.
19. Toussaint, M., & Storkey, A. (2006). Probabilistic inference for solving discrete and continuous state Markov decision processes. In Proc. int. conf. on machine learning.
20. Vlassis, N., & Toussaint, M. (2009). Model-free reinforcement learning as mixture learning. In Proc. int. conf. on machine learning, Montreal, Canada.
21. G. Wei M. Tanner 1990 A Monte Carlo implementation of the EM algorithm and the poor man's data augmentation algorithm Journal of the American Statistical Association 85 699 704 10.2307/2290005