Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics

Autor:	Boetius, David, Leue, Stefan
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Logic in Computer Science
Druh dokumentu:	Working Paper
Popis:	Naively trained Deep Reinforcement Learning agents may fail to satisfy vital safety constraints. To avoid costly retraining, we may desire to repair a previously trained reinforcement learning agent to obviate unsafe behaviour. We devise a counterexample-guided repair algorithm for repairing reinforcement learning systems leveraging safety critics. The algorithm jointly repairs a reinforcement learning agent and a safety critic using gradient-based constrained optimisation. Comment: 7 pages + references
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.15430 Zobrazit plný text záznamu View this record from Arxiv