Approximating Euclidean by Imprecise Markov Decision Processes.
Manfred JaegerGiorgio BacciGiovanni BacciKim Guldstrand LarsenPeter Gjøl JensenPublished in: ISoLA (1) (2020)
Keyphrases
- markov decision processes
- reinforcement learning
- state space
- optimal policy
- finite state
- dynamic programming
- policy iteration
- transition matrices
- finite horizon
- reachability analysis
- reinforcement learning algorithms
- model based reinforcement learning
- euclidean space
- infinite horizon
- partially observable
- average cost
- factored mdps
- planning under uncertainty
- decision theoretic planning
- average reward
- risk sensitive
- action sets
- semi markov decision processes
- decision processes
- discounted reward
- action space
- reward function
- linear programming
- data mining
- long run