Tableaux for Policy Synthesis for MDPs with PCTL* Constraints.
Peter BaumgartnerSylvie ThiébauxFelipe W. TrevizanPublished in: CoRR (2017)
Keyphrases
- optimal policy
- markov decision processes
- markov decision process
- markov decision problems
- policy search
- finite horizon
- reinforcement learning
- average reward
- policy iteration
- average cost
- state and action spaces
- partially observable
- reward function
- modal logic
- state space
- reinforcement learning problems
- initial state
- long run
- planning under uncertainty
- linear program
- constraint satisfaction