Deep Multi Agent Reinforcement Learning for Autonomous Driving

Bhalla, Sushrut; Subramanian, Sriram Ganapathi; Crowley, Mark

doi:10.1007/978-3-030-47358-7_7

Cited by 42 publications

(17 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It could be very beneficial in high-level decision-making and coordination between autonomous vehicles. There have been some prior works that used MARL for AVs [140,141,142].…”

Section: Autonomous and Semi-autonomous Vehiclesmentioning

confidence: 99%

Deep reinforcement learning techniques for vehicular networks: Recent advances and future trends towards 6G

Mekrache

Bradai

Moulay

et al. 2022

Vehicular Communications

View full text Add to dashboard Cite

Employing machine learning into 6G vehicular networks to support vehicular application services is being widely studied and a hot topic for the latest research works in the literature. This article provides a comprehensive review of research works that integrated reinforcement and deep reinforcement learning algorithms for vehicular networks management with an emphasis on vehicular telecommunications issues. Vehicular networks have become an important research area due to their specific features and applications such as standardization, efficient traffic management, road safety, and infotainment. In such networks, network entities need to make decisions to maximize network performance under uncertainty. To achieve this goal, Reinforcement Learning (RL) can effectively solve decision-making problems. However, the state and action spaces are massive and complex in large-scale wireless networks. Hence, RL may not be able to find the best strategy in a reasonable time. Therefore, Deep Reinforcement Learning (DRL) has been developed to combine RL with Deep Learning (DL) to overcome this issue. In this survey, we first present vehicular networks and give a brief overview of RL and DRL concepts. Then we review RL and especially DRL approaches to address emerging issues in 6G vehicular networks. We finally discuss and highlight some unresolved challenges for further study.

show abstract

“…It could be very beneficial in high-level decision-making and coordination between autonomous vehicles. There have been some prior works that used MARL for AVs [140,141,142].…”

Section: Autonomous and Semi-autonomous Vehiclesmentioning

confidence: 99%

Deep reinforcement learning techniques for vehicular networks: Recent advances and future trends towards 6G

Mekrache

Bradai

Moulay

et al. 2022

Vehicular Communications

View full text Add to dashboard Cite

show abstract

“…Bhalla et al [59] learned AVs to better communicate and coordinate on a highway. They measure them against DIAL, a benchmark algorithm that focuses on learning to communicate in cooperative tasks [60].…”

Section: Fully-autonomous Fleetmentioning

confidence: 99%

Multi-agent reinforcement learning for autonomous vehicles: a survey

Dinneweth

Boubezoul

Mandiau

et al. 2022

Auton. Intell. Syst.

View full text Add to dashboard Cite

In the near future, autonomous vehicles (AVs) may cohabit with human drivers in mixed traffic. This cohabitation raises serious challenges, both in terms of traffic flow and individual mobility, as well as from the road safety point of view. Mixed traffic may fail to fulfill expected security requirements due to the heterogeneity and unpredictability of human drivers, and autonomous cars could then monopolize the traffic. Using multi-agent reinforcement learning (MARL) algorithms, researchers have attempted to design autonomous vehicles for both scenarios, and this paper investigates their recent advances. We focus on articles tackling decision-making problems and identify four paradigms. While some authors address mixed traffic problems with or without social-desirable AVs, others tackle the case of fully-autonomous traffic. While the latter case is essentially a communication problem, most authors addressing the mixed traffic admit some limitations. The current human driver models found in the literature are too simplistic since they do not cover the heterogeneity of the drivers’ behaviors. As a result, they fail to generalize over the wide range of possible behaviors. For each paper investigated, we analyze how the authors formulated the MARL problem in terms of observation, action, and rewards to match the paradigm they apply.

show abstract

“…Driven by both, algorithmic advances and the emergence of deep learning [1,2,3], RL has emerged from a conceptual approach to successfully tackling tasks previously deemed infeasible. This includes aspects of robotic manipulation [4,5,6,7], autonomous driving [8,9,10], and mastering combinatorially-hard board games [11,12,13,14].…”

Section: Introductionmentioning

confidence: 99%

Uncovering Instabilities in Variational-Quantum Deep Q-Networks

Maja¹,

Wolf²,

Periyasamy³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep Reinforcement Learning (RL) has considerably advanced over the past decade. At the same time, state-of-the-art RL algorithms require a large computational budget in terms of training time to converge. Recent work has started to approach this problem through the lens of quantum computing, which promises theoretical speed-ups for several traditionally hard tasks. In this work, we examine a class of hybrid quantumclassical RL algorithms that we collectively refer to as variational quantum deep Q-networks (VQ-DQN). We show that VQ-DQN approaches are subject to instabilities that cause the learned policy to diverge, study the extent to which this afflicts reproduciblity of established results based on classical simulation, and perform systematic experiments to identify potential explanations for the observed instabilities. Additionally, and in contrast to most existing work on quantum reinforcement learning, we execute RL algorithms on an actual quantum processing unit (an IBM Quantum Device) and investigate differences in behaviour between simulated and physical quantum systems that suffer from implementation deficiencies. Our experiments show that, contrary to opposite claims in the literature, it cannot be conclusively decided if known quantum approaches, even if simulated without physical imperfections, can provide an advantage as compared to classical approaches. Finally, we provide a robust, universal and well-tested implementation of VQ-DQN as a reproducible testbed for future experiments.

show abstract

Deep Multi Agent Reinforcement Learning for Autonomous Driving

Cited by 42 publications

References 6 publications

Deep reinforcement learning techniques for vehicular networks: Recent advances and future trends towards 6G

Deep reinforcement learning techniques for vehicular networks: Recent advances and future trends towards 6G

Multi-agent reinforcement learning for autonomous vehicles: a survey

Uncovering Instabilities in Variational-Quantum Deep Q-Networks

Contact Info

Product

Resources

About