MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters

no code implementations • 4 Nov 2023 • Mohamed Younes, Ewa Kijak, Richard Kulpa, Simon Malinowski, Franck Multon

In this paper, we propose a novel Multi-Agent Generative Adversarial Imitation Learning based approach that generalizes the idea of motion imitation for one character to deal with both the interaction and the motions of the multiple physics-based characters.

Imitation Learning