First Passage Optimality and Variance Minimisation of Markov Decision Processes with Varying Discount Factors.
Xiao WuXianping GuoPublished in: J. Appl. Probab. (2015)
Keyphrases
- markov decision processes
- average cost
- average reward
- optimal policy
- state space
- reinforcement learning
- finite state
- transition matrices
- finite horizon
- planning under uncertainty
- dynamic programming
- policy iteration
- reachability analysis
- state and action spaces
- factored mdps
- decision theoretic planning
- stationary policies
- infinite horizon
- reinforcement learning algorithms
- semi markov decision processes
- decision processes
- partially observable
- policy evaluation
- risk sensitive
- reward function
- optimal solution
- real time dynamic programming
- action sets
- state abstraction
- markov decision problems
- model based reinforcement learning
- fixed point
- probability distribution
- stochastic shortest path