Unlike AC, DAC can dynamically adjust the algorithm's configuration during

Modeling multi-agent systems requires understanding howagents interact. Such systems are often difficult to model because they can involve a variety of types ofinteractions that layer together todriverich social behavioral dynamics.

To test the efficiency of each component, we remove them separately (LG-ODE-no att,7 LG-ODE-no PE) and find the performances drop. This suggests that distinguishing the importance of nodes w.r.t8 time and incorporating temporal information via learnable positional encoding would benefit model performance.9 ForEqn2, we adopt the GNN model in[2]tocapture the interaction among agents.

In contrast, the mathematics needed to analyze such schemes is what forms the focus in Stochastic Approximation (SA) theory [2, 4]. More generally, SA refers to an iterative scheme that helps find zeroes or optimal points of a function, for which only noisy evaluationsarepossible.

Most existing results only focus on online settings, in which agents can interact with the environment during training.