Multiagent Decision Making For Maritime Traffic Management

Singh, Arambam James; Nguyen, Duc Thien; Kumar, Ajay; Lau, Hoong Chuin

doi:10.1609/aaai.v33i01.33016171

Cited by 12 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, [84] proposes a MAS approach: maritime space is split into a variety of zones organized as nodes of a directed acyclic graph. Waterway traffic management is carried out by traffic control agents, and vessels are represented by individual agents.…”

Section: Waterway Traffic Systemmentioning

confidence: 99%

Literature Review Toward Decentralized Railway Traffic Management

Marcelli

Pellegrini

2021

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

This paper analyses the literature to identify ideas which may be applied to decentralized real-time railway traffic management. This system represents a new way for dealing with railway traffic perturbations in absence of a central decision maker. Specifically, we are interested in identifying techniques that may constitute suitable automatic mechanisms for the emergence of an effective system behaviour. In this literature review, we discuss the possibility of exploiting the existing research works on other transport modes. The analysis of these works makes it clear that real-time railway traffic management is very peculiar. Hence, we consider different approaches: hierarchical self organization, task allocation, reinforcement learning, consensus, auction and coopetition techniques. Some promising possibilities emerge, which we analyse proposing ideas for modelling decentralized real-time railway traffic management.

show abstract

Section: Waterway Traffic Systemmentioning

confidence: 99%

Literature Review Toward Decentralized Railway Traffic Management

Marcelli

Pellegrini

2021

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

show abstract

“…Modeling and simulating large-scale crowd movements [3], including traffic network flows in cities [25,33] and at sea [26], and evacuation from buildings [7,17,32,43] have been actively studied in the field of multi-agent systems. Researchers have exploited multi-agent simulators to find optimal decision-making policies for crowd management.…”

Section: Related Workmentioning

confidence: 99%

“…Crowd movement guidance has been a fascinating problem in various fields, such as easing traffic congestion in normal or abnormal events [25,26,33] and evacuating people from an emergencyaffected areas such as a crowded building [7,17,32,35,43]. To grab the reins of crowds, given a situation, decision-makers need to devote extensive efforts to quickly select guidance that consists of a complex compound of actions.…”

Section: Introductionmentioning

confidence: 99%

Grab the Reins of Crowds: Estimating the Effects of Crowd Movement Guidance Using Causal Inference

Takeuchi,

Nishida,

Kashima

et al. 2021

Preprint

View full text Add to dashboard Cite

Crowd movement guidance has been a fascinating problem in various fields, such as easing traffic congestion in unusual events and evacuating people from an emergency-affected area. To grab the reins of crowds, there has been considerable demand for a decision support system that can answer a typical question: "what will be the outcomes of each of the possible options in the current situation?". In this paper, we consider the problem of estimating the effects of crowd movement guidance from past data. To cope with limited amount of available data biased by past decision-makers, we leverage two recent techniques in deep representation learning for spatial data analysis and causal inference. We use a spatial convolutional operator to extract effective spatial features of crowds from a small amount of data and use balanced representation learning based on the integral probability metrics to mitigate the selection bias and missing counterfactual outcomes. To evaluate the performance on estimating the treatment effects of possible guidance, we use a multi-agent simulator to generate realistic data on evacuation scenarios in a crowded theater, since there are no available datasets recording outcomes of all possible crowd movement guidance. The results of three experiments demonstrate that our proposed method reduces the estimation error by at most 56% from state-of-the-art methods.

show abstract

“…Inspired by advances in deep reinforcement learning (DRL) [1][2][3], many researchers recently focus on utilizing DRL methods to tackle multi-agent problems [4][5][6]. However, most of these works either consider the fully cooperative multi-agent reinforcement learning (MARL) settings [7][8][9][10][11] or generalsum games but make restrictive assumptions about opponents [12][13][14], e.g., either stationary [13] or altruistic [15,16].…”

Section: Introductionmentioning

confidence: 99%

Learning Generalizable Risk-Sensitive Policies to Coordinate in Decentralized Multi-Agent General-Sum Games

Liu¹,

Guo²,

Fang³

2022

Preprint

View full text Add to dashboard Cite

While various multi-agent reinforcement learning methods have been proposed in cooperative settings, few works investigate how self-interested learning agents achieve mutual coordination in decentralized general-sum games and generalize pre-trained policies to non-cooperative opponents during execution. In this paper, we present a generalizable and sample efficient algorithm for multi-agent coordination in decentralized general-sum games without any access to other agents' rewards or observations. Specifically, we first learn the distributions over the return of individuals and estimate a dynamic risk-seeking bonus to encourage agents to discover risky coordination strategies. Furthermore, to avoid overfitting opponents' coordination strategies during training, we propose an auxiliary opponent modeling task so that agents can infer their opponents' type and dynamically alter corresponding strategies during execution. Empirically, we show that agents trained via our method can achieve mutual coordination during training and avoid being exploited by non-cooperative opponents during execution, which outperforms other baseline methods and reaches the state-of-the-art.Preprint. Under review.

show abstract

Multiagent Decision Making For Maritime Traffic Management

Cited by 12 publications

References 15 publications

Literature Review Toward Decentralized Railway Traffic Management

Literature Review Toward Decentralized Railway Traffic Management

Grab the Reins of Crowds: Estimating the Effects of Crowd Movement Guidance Using Causal Inference

Learning Generalizable Risk-Sensitive Policies to Coordinate in Decentralized Multi-Agent General-Sum Games

Contact Info

Product

Resources

About