haiyin piao

multi-agent reinforcement learning (2) proximal policy optimization (2) policy gradient (2) uncertainty quantification (1) policy learning (1) multi-agent learning (1) continuous control (1) off-policy learning (1) policy improvement (1) reward uncertainty (1) exploration strategy (1) optimism-based exploration (1) optimism in face of uncertainty (1) credit assignment (1) reward estimation (1) conservative policy iteration (1) monotonic improvement (1) value distribution (1) noise-aware exploration (1) soft clipping (1)