Formal Language Constraints for Markov Decision Processes.
Eleanor QuintDong XuHaluk DoganZeynep HakguderStephen ScottMatthew B. DwyerPublished in: CoRR (2019)
Keyphrases
- markov decision processes
- formal language
- reinforcement learning
- state space
- optimal policy
- finite state
- transition matrices
- dynamic programming
- formal semantics
- policy iteration
- planning under uncertainty
- reachability analysis
- representation language
- model based reinforcement learning
- state and action spaces
- decision theoretic planning
- partially observable
- average reward
- infinite horizon
- action space
- database
- natural language
- natural language interface
- reward function
- expert systems
- markov decision process
- average cost