Finite approximation of the first passage models for discrete-time Markov decision processes with varying discount factors.
Xiao WuJunyu ZhangPublished in: Discret. Event Dyn. Syst. (2016)
Keyphrases
- markov decision processes
- finite state
- transition matrices
- reinforcement learning
- state and action spaces
- state space
- optimal policy
- semi markov decision processes
- decision theoretic planning
- risk sensitive
- stationary policies
- policy iteration
- reachability analysis
- planning under uncertainty
- reinforcement learning algorithms
- infinite horizon
- partially observable
- finite horizon
- decision processes
- markov models
- model based reinforcement learning
- factored mdps
- dynamic programming
- stochastic shortest path
- decision problems
- markov chain
- probabilistic model
- multi agent