The Complexity of Reachability in Parametric Markov Decision Processes.
Sebastian JungesJoost-Pieter KatoenGuillermo A. PérezTobias WinklerPublished in: CoRR (2020)
Keyphrases
- markov decision processes
- state space
- finite state
- reinforcement learning
- optimal policy
- reinforcement learning algorithms
- transition matrices
- finite horizon
- dynamic programming
- reachability analysis
- planning under uncertainty
- decision theoretic planning
- risk sensitive
- heuristic search
- model based reinforcement learning
- policy iteration
- average reward
- decision processes
- partially observable
- average cost
- decision problems
- action space
- markov decision process
- planning problems
- computational complexity
- action sets
- real time dynamic programming
- total reward
- state and action spaces
- state abstraction
- policy evaluation
- reward function
- infinite horizon
- multi agent