Variable resolution discretization in optimal control

Machine Learning

Volumn 49, Issue 2-3, 2002, Pages 291-323

  Munos, Rémi ^a   Moore, Andrew ^b  

^a CENTRE DE MATHÉMATIQUES APPLIQUÉES   (France)

^b CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

Adaptive mesh refinement; Optimal control; Reinforcement learning; Variable resolution discretization

Indexed keywords

CONVERGENCE OF NUMERICAL METHODS; FINITE DIFFERENCE METHOD; FINITE ELEMENT METHOD; LEARNING SYSTEMS; MARKOV PROCESSES; PARTIAL DIFFERENTIAL EQUATIONS; STATE SPACE METHODS;

ADAPTIVE MESH REFINEMENT; MARKOV DECISION PROCESS; REINFORCEMENT LEARNING; VARIABLE RESOLUTION DISCRETIZATION;

OPTIMAL CONTROL SYSTEMS;

EID: 0036832953     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1017992615625     Document Type: Article

References (43)

1. Residual algorithms: Reinforcement learning with function approximation
2. Gradient descent for general reinforcement learning
3. Convergence of approximation schemes for fully nonlinear second order equations
4. Learning to act using real-time dynamic programming
5. Neuronlike adaptive elements that can learn difficult control problems
6. Minimum-time control of the acrobot
7. Generalization in reinforcement learning: Safely approximating the value function
8. Learning from delayed reinforcement in a complex domain
9. User's guide to viscosity solutions of second order partial differential equations
10. Viscosity solutions of hamilton-jacobi equations
11. Improving elevator performance using reinforcement learning
12. Multidimentional triangulation and interpolation for reinforcement learning
13. Rates of convergence for approximation schemes in optimal control
14. An algorithm for finding best matches in logarithmic expected time
15. Stable function approximation in dynamic programming
16. Adaptive sparse grid multilevel methods for elliptic pdes based on finite differences
17. An adaptive grid scheme for the discrete hamilton-jacobi-bellman equation
18. Instance-based utile distinctions for reinforcement learning with hidden state
19. Exploration of multi-state environments: Local measures and back-propagation of uncertainty
20. Fast learning in networks of locally-tuned processing units
21. Variable resolution dynamic programming: Efficiently learning action maps in multivariate real-valued state-spaces
22. The parti-game algorithm for variable resolution reinforcement learning in multidimensional state space
23. Simplical mesh generation with applications
24. A study of reinforcement learning in the continuous case by the means of viscosity solutions
25. Gradient descent approaches to neural-net-based solutions of the hamilton-jacobi-bellman equation
26. Barycentric interpolators for continuous space and time reinforcement learning
27. Rates of convergence for variable resolution schemes in optimal control
28. Random number generation and quasi-monte carlo methods
29. Numerical dynamic programming in economics
30. A self-learning automation with variable resolution for high precision assembly by industrial robots
31. Generalization in reinforcement learning: Successful examples using sparse coarse coding
32. Temporal difference learning and td-gammon
33. A linear programming approach to solving stochastic dynamic programs
34. An analysis of temporal difference learning with function approximation
35. Sparse grids