Yassine Chemingui

offline reinforcement learning (2) policy optimization (1) gradient descent (1) constraint satisfaction (1) bayesian optimization (1) safe reinforcement learning (1) surrogate model (1) offline optimization (1) model-based optimization (1) materials discovery (1) surrogate modeling (1) reward optimization (1) policy-guided gradient search (1) policy switching (1) reward cost trade-off (1) optimization bia (1)