On the Complexity of Iterative Tropical Computation with Applications to Markov Decision Processes.
Nikhil BalajiStefan KieferPetr NovotnýGuillermo A. PérezMahsa ShirmohammadiPublished in: CoRR (2018)
Keyphrases
- markov decision processes
- optimal policy
- dynamic programming
- state space
- reinforcement learning
- policy iteration
- finite state
- transition matrices
- decision theoretic planning
- markov decision process
- finite horizon
- reachability analysis
- average cost
- decision processes
- planning under uncertainty
- risk sensitive
- partially observable
- average reward
- reinforcement learning algorithms
- computational complexity
- semi markov decision processes
- decision problems
- infinite horizon
- state and action spaces
- data mining
- factored mdps
- search space