Optimal Control of Partially Observable Markov Decision Processes with Finite Linear Temporal Logic Constraints.
Krishna Chaitanya KalagarlaDhruva KartikDongming ShenRahul JainAshutosh NayyarPierluigi NuzzoPublished in: CoRR (2022)
Keyphrases
- optimal control
- linear temporal logic
- partially observable markov decision processes
- dynamic programming
- infinite horizon
- reinforcement learning
- temporal logic
- actor critic
- policy gradient
- control problems
- finite state
- model checking
- control strategy
- belief space
- dynamical systems
- classical planning
- partial observability
- belief state
- optimal policy
- state space
- markov decision processes
- planning problems
- partially observable
- average cost
- policy iteration
- machine learning
- temporal difference
- linear programming
- learning algorithm