flex336
发表于 2025-3-25 06:42:51
http://reply.papertrans.cn/67/6601/660025/660025_21.png
JEER
发表于 2025-3-25 09:54:41
http://reply.papertrans.cn/67/6601/660025/660025_22.png
Introvert
发表于 2025-3-25 14:23:34
http://reply.papertrans.cn/67/6601/660025/660025_23.png
nuclear-tests
发表于 2025-3-25 18:43:37
Open- and Closed-Loop Neural Network Verification Using Polynomial Zonotopes,tangent activation functions. In particular, we abstract the input-output relation of each neuron by a polynomial approximation, which is evaluated in a set-based manner using polynomial zonotopes. While our approach can also can be beneficial for open-loop neural network verification, our main appl
hemoglobin
发表于 2025-3-25 23:25:19
http://reply.papertrans.cn/67/6601/660025/660025_25.png
LIMN
发表于 2025-3-26 03:44:50
http://reply.papertrans.cn/67/6601/660025/660025_26.png
BILL
发表于 2025-3-26 08:20:10
http://reply.papertrans.cn/67/6601/660025/660025_27.png
描述
发表于 2025-3-26 11:19:51
Strategy Synthesis in Markov Decision Processes Under Limited Sampling Access, partially unknown environments. In environments modeled by . Markov decision processes (MDPs), the impact of the agents’ actions are known in terms of successor states but not the stochastics involved. In this paper, we devise a strategy synthesis algorithm for gray-box MDPs via reinforcement learn
贪心
发表于 2025-3-26 14:17:30
http://reply.papertrans.cn/67/6601/660025/660025_29.png
dapper
发表于 2025-3-26 17:08:50
,Reward Shaping from Hybrid Systems Models in Reinforcement Learning,equirements, formal methods for learning-enabled systems, such as closed-loop neural network verification, shielding, falsification, and online reachability analysis, analyze learned controllers for safety violations. Besides filtering unsafe actions during training, these approaches view verificati