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

03/14/2019
by   Raunak P. Bhattacharyya, et al.
0

Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such behaviors arise due to the many local interactions between agents that are not commonly accounted for in imitation learning. This paper proposes Reward Augmented Imitation Learning (RAIL), which integrates reward augmentation into the multi-agent imitation learning framework and allows the designer to specify prior knowledge in a principled fashion. We prove that convergence guarantees for the imitation learning process are preserved under the application of reward augmentation. This method is validated in a driving scenario, where an entire traffic scene is controlled by driving policies learned using our proposed algorithm. Further, we demonstrate improved performance in comparison to traditional imitation learning algorithms both in terms of the local actions of a single agent and the behavior of emergent properties in complex, multi-agent settings.

READ FULL TEXT

page 1

page 2

page 6

research
01/04/2020

Multi-Agent Interactions Modeling with Correlated Policies

In multi-agent systems, complex interacting behaviors arise due to the h...
research
06/10/2020

Modeling Human Driving Behavior through Generative Adversarial Imitation Learning

Imitation learning is an approach for generating intelligent behavior wh...
research
03/02/2018

Multi-Agent Imitation Learning for Driving Simulation

Simulation is an appealing option for validating the safety of autonomou...
research
06/10/2023

Long-term Microscopic Traffic Simulation with History-Masked Multi-agent Imitation Learning

A realistic long-term microscopic traffic simulator is necessary for und...
research
09/21/2023

Learning to Drive Anywhere

Human drivers can seamlessly adapt their driving decisions across geogra...
research
06/19/2020

Modelling Agent Policies with Interpretable Imitation Learning

As we deploy autonomous agents in safety-critical domains, it becomes im...
research
06/11/2017

Meta learning Framework for Automated Driving

The success of automated driving deployment is highly depending on the a...

Please sign up or login with your details

Forgot password? Click here to reset