On the Relationship Between Satisfiability and Markov Decision Processes.
Ricardo SalmonPascal PoupartPublished in: UAI (2019)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- policy iteration
- reinforcement learning
- dynamic programming
- transition matrices
- risk sensitive
- reinforcement learning algorithms
- np complete
- decision theoretic planning
- infinite horizon
- decision processes
- markov decision process
- average reward
- average cost
- factored mdps
- state and action spaces
- finite horizon
- partially observable
- action sets
- reachability analysis
- model based reinforcement learning
- data mining
- action space
- planning under uncertainty
- computational complexity