mlsanityData to 7 Oct 2026

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

arXiv 2311.02502 ↗First posted 4 Nov 2023cs.CV cs.AI cs.GRcited by 2

On the map: Offline RL and imitation learning from data → Imitation learning methods

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.

Key facts. Cited by 2 papers in the map (data through 7 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.

Builds on

21 of 63 references.

Closest ancestors · 3

Same direction, newest first

  1. 2021A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control21 May
  2. 2018Multi-Agent Generative Adversarial Imitation Learning26 Jul
  3. 2018Generative Adversarial Imitation from Observation17 Jul

Other references · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  4. 2016Generative Adversarial Imitation Learningcited by 1,576
  5. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  6. 2016Least Squares Generative Adversarial Networkscited by 1,000
  7. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  8. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  9. 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
  10. 2017Robust Imitation of Diverse Behaviorscited by 85
  11. 2021Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharingcited by 85
  12. 2017Learning human behaviors from motion capture by adversarial imitationcited by 75
6 more
  1. 2017Dual Discriminator Generative Adversarial Netscited by 55
  2. 2018MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasetscited by 49
  3. 2023PADL: Language-Directed Physics-Based Character Controlcited by 47
  4. 2020ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skillscited by 44
  5. 2023Animating Human Athleticscited by 16
  6. 2021Discovering Diverse Athletic Jumping Strategiescited by 15

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2025Versatile Physics-based Character Control with Hybrid Latent Representationcited by 3
  2. 2024AI-Guided Molecular Simulations in VR: Exploring Strategies for Imitation Learning in Hyperdimensional Molecular Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
  2. 2021AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
  3. 2023Synthesizing Physical Character-Scene Interactions
  4. 2023Generating Personas for Games with Multimodal Adversarial Imitation Learning
  5. 2025SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
  6. 2023CALM: Conditional Adversarial Latent Models for Directable Virtual Characters
  7. 2021RAIL: A modular framework for Reinforcement-learning-based Adversarial Imitation Learning
  8. 2023C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters