Markov decision processes under observability constraints.
Yasemin SerinVidyadhar G. KulkarniPublished in: Math. Methods Oper. Res. (2005)
Keyphrases
- markov decision processes
- partially observable
- optimal policy
- finite state
- state space
- reinforcement learning
- dynamic programming
- reachability analysis
- finite horizon
- transition matrices
- policy iteration
- reinforcement learning algorithms
- decision theoretic planning
- average cost
- markov decision process
- decision processes
- planning under uncertainty
- factored mdps
- risk sensitive
- infinite horizon
- reward function
- model based reinforcement learning
- action space
- long run
- action sets
- interval estimation
- decision problems
- semi markov decision processes
- function approximation
- state and action spaces
- stationary policies
- probabilistic planning