Qisong Yang

reinforcement learning (2) neural network optimization (1) continuous control (1) constraint satisfaction (1) entropy maximization (1) worst-case optimization (1) k-nearest neighbor (1) conditional value-at-risk (1) safety constraint (1) activation function (1) policy network (1) task-agnostic exploration (1) risk control (1) safe exploration (1) state entropy (1) state space generalization (1) soft actor critic (1) deep reinforcement learning (1) safety-constrained reinforcement learning (1)