An Approximate Stochastic Annealing algorithm for finite horizon Markov decision processes.
Jiaqiao HuHyeong Soo ChangPublished in: CDC (2010)
Keyphrases
- markov decision processes
- finite horizon
- annealing algorithm
- control policies
- optimal policy
- infinite horizon
- deterministic annealing
- protein folding
- finite state
- markov decision process
- state space
- average cost
- dynamic programming
- reinforcement learning
- policy iteration
- simulated annealing
- long run
- state dependent
- stochastic model
- partially observable
- objective function
- search space
- lost sales
- optimal control
- decision problems
- semi supervised