Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines.
Xuejing ZhengChao YuChen ChenJianye HaoHankz Hankui ZhuoPublished in: CoRR (2021)
Keyphrases
- temporal logic
- reinforcement learning
- model checking
- modal logic
- modal operators
- linear time temporal logic
- function approximation
- concurrent systems
- reward function
- satisfiability problem
- reinforcement learning algorithms
- state space
- belief revision
- markov decision processes
- optimal policy
- transition systems
- multi agent
- predicate logic
- mazurkiewicz traces
- verification method
- partially observable
- average reward
- learning algorithm
- computation tree logic
- bounded model checking
- linear temporal logic
- logical formulas
- model free
- learning agent
- dynamic programming
- multi agent systems
- temporally extended
- policy gradient
- model checker
- search algorithm
- markov decision process
- automata theoretic
- formal specification language