Discretized Approximations for POMDP with Average Cost.
Huizhen YuDimitri P. BertsekasPublished in: UAI (2004)
Keyphrases
- average cost
- finite state
- markov decision processes
- optimal policy
- policy evaluation
- infinite horizon
- markov decision process
- markov decision problems
- partially observable markov decision processes
- long run
- policy iteration
- partially observable
- state space
- finite number
- markov chain
- approximate dynamic programming
- finite horizon
- markov decision chains
- optimal control
- reinforcement learning
- inventory models
- dynamic programming
- decision problems
- initial state
- state dependent
- multistage
- model checking
- linear programming
- total cost
- risk sensitive
- linear program
- action sets
- mathematical model
- average reward
- data mining
- sufficient conditions
- special case
- partially observable markov decision process