Solving Markov Decision Processes with Reachability Characterization from Mean First Passage Times.
Shoubhik DebnathLantao LiuGaurav S. SukhatmePublished in: IROS (2018)
Keyphrases
- markov decision processes
- state space
- transition matrices
- semi markov decision processes
- optimal policy
- decision theoretic planning
- reinforcement learning
- finite state
- markov decision problems
- reinforcement learning algorithms
- reachability analysis
- policy iteration
- dynamic programming
- planning under uncertainty
- average reward
- infinite horizon
- decision processes
- model based reinforcement learning
- policy iteration algorithm
- action sets
- stochastic shortest path
- risk sensitive
- action space
- finite horizon
- reward function
- markov chain
- factored mdps
- average cost
- partially observable
- state and action spaces
- heuristic search
- markov decision process
- dynamical systems
- data mining