Multi-Agent Interactions Modeling with Correlated Policies

01/04/2020
by   Minghuan Liu, et al.
0

In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence among policies and their reward structures. In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents' policies, which can recover agents' policies that can regenerate similar interactions. Consequently, we develop a Decentralized Adversarial Imitation Learning algorithm with Correlated policies (CoDAIL), which allows for decentralized training and execution. Various experiments demonstrate that CoDAIL can better regenerate complex interactions close to the demonstrators and outperforms state-of-the-art multi-agent imitation learning methods.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 10

page 19

page 20

03/14/2019

Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning

Recent developments in multi-agent imitation learning have shown promisi...
07/10/2021

Multi-Agent Imitation Learning with Copulas

Multi-agent imitation learning aims to train multiple agents to perform ...
03/12/2019

Imitation Learning of Factored Multi-agent Reactive Models

We apply recent advances in deep generative modeling to the task of imit...
06/19/2020

Modelling Agent Policies with Interpretable Imitation Learning

As we deploy autonomous agents in safety-critical domains, it becomes im...
06/24/2019

Learning to Interactively Learn and Assist

When deploying autonomous agents in the real world, we need to think abo...
01/05/2022

Conditional Imitation Learning for Multi-Agent Games

While advances in multi-agent learning have enabled the training of incr...
09/10/2018

PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning

Multi-agent path finding (MAPF) is an essential component of many large-...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.