Constrained optimality problem of Markov decision processes with Borel spaces and varying discount factors.
Xiao WuYanqiu TangPublished in: Kybernetika (2021)
Keyphrases
- markov decision processes
- average cost
- average reward
- stationary policies
- state space
- reinforcement learning
- optimal policy
- finite state
- transition matrices
- reinforcement learning algorithms
- dynamic programming
- policy iteration
- model based reinforcement learning
- markov decision process
- infinite horizon
- finite horizon
- planning under uncertainty
- partially observable
- risk sensitive
- decision theoretic planning
- reward function
- factored mdps
- action space
- decision problems
- state and action spaces
- action sets
- reachability analysis
- semi markov decision processes
- heuristic search
- optimal solution
- optimality criterion
- data mining