Seungyub Han

deep reinforcement learning (1) reinforcement learning (1) continual learning (1) catastrophic forgetting (1) offline reinforcement learning (1) nonconvex optimization (1) policy optimization (1) distributional reinforcement learning (1) continuous control (1) sequential learning (1) variance estimation (1) optimistic exploration (1) bilevel optimization (1) random matrix theory (1) convergence guarantee (1) ensemble method (1) atari game (1) risk constraint (1) spectral risk measure (1) worst-case scenario (1)