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

arXiv: https://arxiv.org/abs/2311.02502 · HTML: https://mlsanity.com/paper/2311.02502/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 21 of its 63 references that are in the map.
- First posted on arXiv 4 Nov 2023.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Generative Adversarial Imitation from Observation](https://mlsanity.com/paper/1807.06158/) (2018)
- [Multi-Agent Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1807.09936/) (2018)
- [Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing](https://mlsanity.com/paper/2102.07475/) (2021)
- [From Motor Control to Team Play in Simulated Humanoid Football](https://mlsanity.com/paper/2105.12196/) (2021)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [Learning human behaviors from motion capture by adversarial imitation](https://mlsanity.com/paper/1707.02201/) (2017)
- [Dual Discriminator Generative Adversarial Nets](https://mlsanity.com/paper/1709.03831/) (2017)
- [ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills](https://mlsanity.com/paper/2005.04323/) (2020)
- [MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets](https://mlsanity.com/paper/1811.03850/) (2018)
- [PADL: Language-Directed Physics-Based Character Control](https://mlsanity.com/paper/2301.13868/) (2023)
- [Animating Human Athletics](https://mlsanity.com/paper/2302.06108/) (2023)
- [Discovering Diverse Athletic Jumping Strategies](https://mlsanity.com/paper/2105.00371/) (2021)
- [A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control](https://mlsanity.com/paper/2105.10066/) (2021)

## Built on by (most cited first, 2 of 2)

- [Versatile Physics-based Character Control with Hybrid Latent Representation](https://mlsanity.com/paper/2503.12814/) (2025)
- [AI-Guided Molecular Simulations in VR: Exploring Strategies for Imitation Learning in Hyperdimensional Molecular Systems](https://mlsanity.com/paper/2409.07189/) (2024)

## Abstract (arXiv)

Simulating realistic interaction and motions for physics-based characters is of great interest for interactive applications, and automatic secondary character animation in the movie and video game industries. Recent works in reinforcement learning have proposed impressive results for single character simulation, especially the ones that use imitation learning based techniques. However, imitating multiple characters interactions and motions requires to also model their interactions. 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. Two unstructured datasets are given as inputs: 1) a single-actor dataset containing motions of a single actor performing a set of motions linked to a specific application, and 2) an interaction dataset containing a few examples of interactions between multiple actors. Based on these datasets, our system trains control policies allowing each character to imitate the interactive skills associated with each actor, while preserving the intrinsic style. This approach has been tested on two different fighting styles, boxing and full-body martial art, to demonstrate the ability of the method to imitate different styles.