DeepAI
Log In Sign Up

Multi-Agent Imitation Learning with Copulas

07/10/2021
by   Hongwei Wang, et al.
7

Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions, which is essential for understanding physical, social, and team-play systems. However, most existing works on modeling multi-agent interactions typically assume that agents make independent decisions based on their observations, ignoring the complex dependence among agents. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents. Extensive experiments on synthetic and real-world datasets show that our model outperforms state-of-the-art baselines across various scenarios in the action prediction task, and is able to generate new trajectories close to expert demonstrations.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/04/2020

Multi-Agent Interactions Modeling with Correlated Policies

In multi-agent systems, complex interacting behaviors arise due to the h...
03/04/2019

Modeling Social Group Communication with Multi-Agent Imitation Learning

In crowded social scenarios with a myriad of external stimuli, human bra...
07/26/2018

Multi-Agent Generative Adversarial Imitation Learning

Imitation learning algorithms can be used to learn a policy from expert ...
05/05/2022

Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations

We present Bayesian Team Imitation Learner (BTIL), an imitation learning...
01/05/2022

Conditional Imitation Learning for Multi-Agent Games

While advances in multi-agent learning have enabled the training of incr...
03/20/2018

Generative Multi-Agent Behavioral Cloning

We propose and study the problem of generative multi-agent behavioral cl...
06/26/2018

Learning Social Conventions in Markov Games

Social conventions - arbitrary ways to organize group behavior - are an ...