A Solution to Time-Varying Markov Decision Processes.
Lantao LiuGaurav S. SukhatmePublished in: IEEE Robotics Autom. Lett. (2018)
Keyphrases
- markov decision processes
- optimal policy
- reinforcement learning
- finite state
- policy iteration
- state space
- reachability analysis
- transition matrices
- decision theoretic planning
- average cost
- dynamic programming
- factored mdps
- partially observable
- infinite horizon
- reinforcement learning algorithms
- decision processes
- average reward
- markov decision process
- planning under uncertainty
- finite horizon
- state and action spaces
- machine learning
- model checking
- model based reinforcement learning
- semi markov decision processes
- optimal solution
- action space
- least squares
- markov chain