The Complexity of Uncertainty in Markov Decision Processes.
Dimitri ScheftelowitschPublished in: SIAM Conf. on Control and its Applications (2015)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- reinforcement learning
- transition matrices
- planning under uncertainty
- decision theoretic planning
- decision problems
- policy iteration
- dynamic programming
- reinforcement learning algorithms
- reachability analysis
- finite horizon
- state and action spaces
- factored mdps
- action space
- infinite horizon
- partially observable
- decision processes
- average reward
- reward function
- markov decision process
- risk sensitive
- action sets
- average cost
- computational complexity
- state abstraction
- decision diagrams
- multistage