Verifiable RNN-Based Policies for POMDPs Under Temporal Logic Constraints.
Steven CarrNils JansenUfuk TopcuPublished in: CoRR (2020)
Keyphrases
- temporal logic
- model checking
- partially observable markov decision processes
- automata theoretic
- dynamic constraints
- finite state
- temporally extended
- modal logic
- optimal policy
- satisfiability problem
- concurrent systems
- verification method
- nearest neighbor
- recurrent neural networks
- linear temporal logic
- policy search
- reinforcement learning
- reactive systems
- belief revision
- temporal knowledge
- formal specification language
- temporally extended goals
- computation tree logic
- belief state
- mazurkiewicz traces
- query answering
- linear programming
- dynamic programming