Interaction-Aware Multi-Agent Reinforcement Learning for Mobile Agents with Individual Goals

Mohseni-Kabir, Anahita; Isele, David; Fujimura, Kikuo

doi:10.1109/icra.2019.8793721

Cited by 11 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A Markov game (MG) is also used for modeling interaction scenarios. According to whether agents have the same importance, methods can be categorized into three groups: 1) equal importance [157,168,169], 2) one vs. others [170], and 3) proactivepassive pair [171].…”

Section: ) Interaction Modelingmentioning

confidence: 99%

A Survey of Deep RL and IL for Autonomous Driving Policy Learning

Zhu,

Zhao

2021

Preprint

View full text Add to dashboard Cite

Autonomous driving (AD) agents generate driving policies based on online perception results, which are obtained at multiple levels of abstraction, e.g., behavior planning, motion planning and control. Driving policies are crucial to the realization of safe, efficient and harmonious driving behaviors, where AD agents still face substantial challenges in complex scenarios. Due to their successful application in fields such as robotics and video games, the use of deep reinforcement learning (DRL) and deep imitation learning (DIL) techniques to derive AD policies have witnessed vast research efforts in recent years. This paper is a comprehensive survey of this body of work, which is conducted at three levels: First, a taxonomy of the literature studies is constructed from the system perspective, among which five modes of integration of DRL/DIL models into an AD architecture are identified. Second, the formulations of DRL/DIL models for conducting specified AD tasks are comprehensively reviewed, where various designs on the model state and action spaces and the reinforcement learning rewards are covered. Finally, an in-depth review is conducted on how the critical issues of AD applications regarding driving safety, interaction with other traffic participants and uncertainty of the environment are addressed by the DRL/DIL models. To the best of our knowledge, this is the first survey to focus on AD policy learning using DRL/DIL, which is addressed simultaneously from the system, task-driven and problem-driven perspectives. We share and discuss findings, which may lead to the investigation of various topics in the future.

show abstract

Section: ) Interaction Modelingmentioning

confidence: 99%

A Survey of Deep RL and IL for Autonomous Driving Policy Learning

Zhu,

Zhao

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Chen et al [22] investigate the application of different model-free reinforcement learning approaches on urban driving scenarios. Mohseni-Kabir et al [4] use multi-agent reinforcement learning to model the interactions between different drivers. Isele et al [3] explore the use of deep Q learning [23] on the intersection scenario with an emphasis on occluded vehicles.…”

Section: Related Workmentioning

confidence: 99%

“…Deep reinforcement learning (DRL) has shown promising performance on various control and decision making tasks including robotics [1], games [2], and autonomous driving [3], [4]. Compared with traditional rule-based [5], [6] or optimization-based approaches [7], [8] to autonomous driving, DRL methods have the potential for better scalability and generalization in complex scenarios that require observing subtle changes in behavior and executing complex interactions with other agents [9]- [11].…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships

Kochenderfer

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Deep reinforcement learning (DRL) provides a promising way for learning navigation in complex autonomous driving scenarios. However, identifying the subtle cues that can indicate drastically different outcomes remains an open problem with designing autonomous systems that operate in human environments. In this work, we show that explicitly inferring the latent state and encoding spatial-temporal relationships in a reinforcement learning framework can help address this difficulty. We encode prior knowledge on the latent states of other drivers through a framework that combines the reinforcement learner with a supervised learner. In addition, we model the influence passing between different vehicles through graph neural networks (GNNs). The proposed framework significantly improves performance in the context of navigating T-intersections compared with state-of-the-art baseline approaches.

show abstract

“…Training in simulation rarely transfers [14], [15]. And transfer is likely to be worse in the case of stochastic games which are known to stereotype to the behavior of the agents they are trained against [16], [17], [18]. Working with the game trees directly produces interpretable decisions which are better suited to safety guarantees, and ease the debugging of undesirable behavior.…”

Section: Davidmentioning

confidence: 99%

Interactive Decision Making for Autonomous Vehicles in Dense Traffic

Isele

2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

Self Cite

View full text Add to dashboard Cite

Dense urban traffic environments can produce situations where accurate prediction and dynamic models are insufficient for successful autonomous vehicle motion planning. We investigate how an autonomous agent can safely negotiate with other traffic participants, enabling the agent to handle potential deadlocks. Specifically we consider merges where the gap between cars is smaller than the size of the ego vehicle. We propose a game theoretic framework capable of generating and responding to interactive behaviors. Our main contribution is to show how game-tree decision making can be executed by an autonomous vehicle, including approximations and reasoning that make the tree-search computationally tractable. Additionally, to test our model we develop a stochastic rule-based traffic agent capable of generating interactive behaviors that can be used as a benchmark for simulating traffic participants in a crowded merge setting.

show abstract

Interaction-Aware Multi-Agent Reinforcement Learning for Mobile Agents with Individual Goals

Cited by 11 publications

References 24 publications

A Survey of Deep RL and IL for Autonomous Driving Policy Learning

A Survey of Deep RL and IL for Autonomous Driving Policy Learning

Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships

Interactive Decision Making for Autonomous Vehicles in Dense Traffic

Contact Info

Product

Resources

About