Optimal control of partially observable Markov decision processes with finite linear temporal logic constraints.
Krishna Chaitanya KalagarlaKartik DhruvaDongming ShenRahul JainAshutosh NayyarPierluigi NuzzoPublished in: UAI (2022)
Keyphrases
- optimal control
- linear temporal logic
- partially observable markov decision processes
- infinite horizon
- dynamic programming
- reinforcement learning
- temporal logic
- model checking
- policy gradient
- actor critic
- finite state
- control problems
- belief space
- state space
- control strategy
- markov decision processes
- planning problems
- dynamical systems
- belief state
- partially observable
- average cost
- decision problems
- partial observability
- hidden state
- fully observable
- machine learning
- finite number
- average reward
- knowledge base
- constraint programming
- optimal policy
- linear programming
- decision makers
- lower bound