Filters








2 Hits in 3.2 sec

Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications [article]

Giuseppe De Giacomo and Luca Iocchi and Marco Favorito and Fabio Patrizi
2019 arXiv   pre-print
We consider the case in which the agent is a reinforcement learning agent on the first set of features, while the restraining bolt is specified logically using linear time logic on finite traces LTLf/LDLf  ...  We show formally, and illustrate with examples, that, under general circumstances, the agent can learn while shaping its goals to suitably conform (as much as possible) to the restraining bolt specifications  ...  With this specification, the agent can just learn how to move in the grid, but it cannot match related concepts. Restraining bolt.  ... 
arXiv:1807.06333v2 fatcat:jl2rnvs7zrg25pvubjcpljwiei

Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf Restraining Specifications

Giuseppe De Giacomo, Luca Iocchi, Marco Favorito, Fabio Patrizi
2020 Zenodo  
We consider the case in which the agent is a reinforcement learning agent on the first set of features, while the restraining bolt is specified logically using linear time logic on finite traces LTLf/LDLf  ...  We show formally, and illustrate with examples, that, under general circumstances, the agent can learn while shaping its goals to suitably conform (as much as possible) to the restraining bolt specifications  ...  Conclusions We have shown how to perform RL with LTL f /LDL f restraining specifications by resorting to typical RL techniques based on MDPs.  ... 
doi:10.5281/zenodo.3944779 fatcat:jp25lvvx5ndcdi75jmdp3b7vdm