Reachable Space Characterization of Markov Decision Processes with Time Variability.
Junhong XuKai YinLantao LiuPublished in: CoRR (2019)
Keyphrases
- markov decision processes
- action space
- finite state
- state space
- optimal policy
- transition matrices
- reinforcement learning
- decision theoretic planning
- policy iteration
- risk sensitive
- dynamic programming
- finite horizon
- reachability analysis
- average cost
- reinforcement learning algorithms
- decision processes
- infinite horizon
- action sets
- average reward
- factored mdps
- state and action spaces
- model based reinforcement learning
- markov decision process
- planning under uncertainty
- partially observable
- stochastic shortest path
- semi markov decision processes
- reward function
- multi agent