Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Gagné, Madeleine"'
Autor:
Villalobos-Arias, Leonardo, Martin, Derek, Krishnan, Abhijeet, Gagné, Madeleine, Potts, Colin M., Jhala, Arnav
Safe reinforcement learning deals with mitigating or avoiding unsafe situations by reinforcement learning (RL) agents. Safe RL approaches are based on specific risk representations for particular problems or domains. In order to analyze agent behavio
Externí odkaz:
http://arxiv.org/abs/2312.05231
