yingnan zhao

deep reinforcement learning (2) contrastive learning (1) reinforcement learning (1) data poisoning (1) locomotion control (1) backdoor defense (1) knowledge distillation (1) convergence analysis (1) policy learning (1) distributional reinforcement learning (1) policy iteration (1) adaptive control (1) quasi-newton method (1) sinkhorn divergence (1) wasserstein loss (1) bellman return distribution (1) deep rl (1) multi-behavior learning (1) neural network (1) anderson mixing (1)