Weidong Huang

safe reinforcement learning (2) policy gradient (1) constraint optimization (1) policy learning (1) distributed optimization (1) ai safety (1) risk minimization (1) constraint satisfaction (1) model-based reinforcement learning (1) robot control (1) gradient compression (1) safety benchmark (1) error compensation (1) agent system (1) agent safety (1) safe policy optimization (1) differentiable environment (1) sobolev training (1) policy optimization (1) quantized stochastic gradient descent (1)