Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic

TL;DR

This paper introduces a scalable multi-agent reinforcement learning framework for autonomous vehicle highway on-ramp merging in mixed traffic, improving safety and efficiency through innovative cooperation and safety mechanisms.

Contribution

It presents a novel MARL framework with parameter sharing, local rewards, action masking, and a safety supervisor for effective on-ramp merging in mixed traffic environments.

Findings

Outperforms state-of-the-art benchmarks in simulations

Reduces collision rates significantly

Accelerates training with curriculum learning

Abstract

On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs). In this paper, we formulate the mixed-traffic highway on-ramp merging problem as a multi-agent reinforcement learning (MARL) problem, where the AVs (on both merge lane and through lane) collaboratively learn a policy to adapt to HDVs to maximize the traffic throughput. We develop an efficient and scalable MARL framework that can be used in dynamic traffic where the communication topology could be time-varying. Parameter sharing and local rewards are exploited to foster inter-agent cooperation while achieving great scalability. An action masking scheme is employed to improve learning efficiency by filtering out invalid/unsafe actions at each step. In addition, a novel priority-based safety supervisor is developed to significantly reduce collision rate and greatly expedite the training process. A gym-like simulation environment is developed and open-sourced with three different levels of traffic densities. We exploit curriculum learning to efficiently learn harder tasks from trained models under simpler settings. Comprehensive experimental results show the proposed MARL framework consistently outperforms several state-of-the-art benchmarks.