Opponent modeling is a longstanding research topic aimed at enhancing decision-making by modeling information about opponents in multi-agent environments. However, existing approaches often face challenges such as having difficulty generalizing to unknown opponent policies and conducting unstable performance.

We introduce Neural Conditional Probability (NCP), an operator-theoretic approach to learning conditional distributions with a focus on statistical inference tasks.

To realize this possibility, we observe that a neural network classifier with N parameters can be interpreted as a weighted ensemble of N classifiers, and that in the lazy regime limit these classifiers are fixed throughout learning.

Reinforcement Learning (RL) with function approximation has achieved remarkable success in various applications involving large state and action spaces, such as games [Silver et al., 2016],

Additionally, MBD's ability to integrate with data enhances its versatility and