2 papers
cs.LG2026
Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learning
Vincent Taboga, Justin Veilleux, Doseok Jang +2
Reinforcement learning (RL) has achieved strong results in control, yet learned policies remain brittle to changes in dynamics, action spaces, observation spaces, or goals, a criti…
cs.LG2020
A priori guarantees of finite-time convergence for Deep Neural Networks
Anushree Rankawat, Mansi Rankawat, Harshal B. Oza
In this paper, we perform Lyapunov based analysis of the loss function to derive an a priori upper bound on the settling time of deep neural networks. While previous studies have a…