Ziqian Zhang

multi-agent reinforcement learning (2) continual learning (1) catastrophic forgetting (1) preference learning (1) adversarial attack (1) diffusion model (1) disentangled representation (1) reward model (1) evolutionary algorithm (1) multi-objective reinforcement learning (1) recommendation system (1) non-stationary environment (1) cooperative multi-agent reinforcement learning (1) decentralized execution (1) policy robustness (1) policy change (1) conditional diffusion (1) guided diffusion (1) user distribution (1) adversarial attacker (1)