Efficient approximate planning in continuous space Markovian decision problems

AI Communications

Volumn 14, Issue 3, 2001, Pages 163-176

  Szepesvari C ^a  

^a Mindmaker Ltd   (Hungary)

Author keywords

Markovian Decision Problems; Monte Carlo algorithms; Planning; Value iteration

Indexed keywords

COMPUTATIONAL COMPLEXITY; DECISION THEORY; ITERATIVE METHODS; MARKOV PROCESSES; MONTE CARLO METHODS; PLANNING; PROBABILITY; THEOREM PROVING;

MARKOVIAN DECISION PROBLEMS; MONTE CARLO PLANNING ALGORITHMS; VALUE ITERATION;

ALGORITHMS;

EID: 0034759906     PISSN: 09217126     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (14)

1. The complexity of dynamic programming
2. An optimal multigrid algorithm for continuous state discrete time stochastic control
3. A probabilistic theory of pattern recognition
4. Approximate planning in large POMDPs via reusable trajectories
5. A sparse sampling algorithm for near-optimal planning in large Markovian decision processes
6. Structural estimation of Markov decision processes
7. Using randomization to break the curse of dimensionality
8. Tight performance bounds on greedy policies based on imperfect value functions