Lifelong reinforcement learning with temporal logic formulas and reward machines.
Xuejing ZhengChao YuMinjie ZhangPublished in: Knowl. Based Syst. (2022)
Keyphrases
- temporal logic
- reinforcement learning
- model checking
- modal logic
- function approximation
- modal operators
- concurrent systems
- satisfiability problem
- linear time temporal logic
- state space
- markov decision processes
- logical formulas
- computation tree logic
- reward function
- reinforcement learning algorithms
- average reward
- linear temporal logic
- mazurkiewicz traces
- verification method
- learning algorithm
- model checker
- predicate logic
- model free
- multi agent
- formal verification
- reactive systems
- markov decision process
- finite state
- dynamic constraints
- belief revision
- dynamic programming
- function approximators
- learning agent
- transition systems
- bounded model checking
- optimal policy
- automata theoretic