Zifan Wu

model-based reinforcement learning (2) multi-step prediction (2) model rollout (2) multi-agent reinforcement learning (2) policy gradient (1) uncertainty quantification (1) nash equilibrium (1) multi-agent learning (1) policy improvement (1) safe reinforcement learning (1) trajectory distribution (1) prediction error (1) proximal policy optimization (1) trajectory generation (1) credit assignment (1) budget constraint (1) fictitious play (1) local model (1) monotonic improvement (1) behavioural diversity (1)