Chenghao Li

deep reinforcement learning (1) multi-agent reinforcement learning (1) vision transformer (1) offline reinforcement learning (1) policy optimization (1) mutual information (1) parameter sharing (1) value estimation (1) competitive game (1) extrapolation error (1) softmax approximation (1) multi-party computation (1) risk-sensitive reinforcement learning (1) diverse behavior (1) private inference (1) multi-agent system (1) implicit constraint (1) coordination capacity (1)