Linearly-solvable Markov decision problems

Advances in Neural Information Processing Systems

Volumn , Issue , 2007, Pages 1369-1376

  Todorov, Emanuel ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ANALYTICAL COMPUTATIONS; ARBITRARY PRECISION; BELLMAN EQUATIONS; CONTINUOUS CONTROL; CONTROL COSTS; DISCRETE STATE SPACE; KL-DIVERGENCE; LARGEST EIGENVALUES; LP RELAXATION; MARKOV DECISION PROBLEM; MINIMIZATION PROBLEMS; OPTIMAL CONTROLS; OPTIMAL VALUE FUNCTIONS; Q-LEARNING; RESCALING; SHORTEST PATH PROBLEM; TRANSITION PROBABILITIES;

ALGORITHMS; EIGENVALUES AND EIGENFUNCTIONS; GRAPH THEORY; INTEGER PROGRAMMING; LINEAR TRANSFORMATIONS; MARKOV PROCESSES; OPTIMAL SYSTEMS;

REINFORCEMENT LEARNING;

EID: 84864055301     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. B. Scholkopf and A. Smola, Learning with kernels. MIT Press (2002)
2. S. Boyd and L. Vandenberghe, Convex optimization. Cambridge University Press (2004)
3. D. Bertsekas, Dynamic programming and optimal control (2nd ed). Athena Scientific (2000)
4. F. Chung, Spectral graph theory. CMBS Regional Conference Series in Mathematics (1997)