A multiagent reinforcement learning approach to en-route trip building

Bazzan, Ana L. C.; Grunitzki, Ricardo

doi:10.1109/ijcnn.2016.7727899

Cited by 22 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A. L. C. Bazzan et al [60] considered DTA with individual drivers as independent and autonomous agents, which employ QL to stepwise select suitable routes. According to the objective function of DTA, R. Grunitzki et al [61] proposed two improved algorithms based on QL to maximize the utility of agent and system respectively.…”

Section: B Multi-agent Reinforcement Learning (Marl)mentioning

confidence: 99%

“…Therefore, defining the reward function reasonably is more suitable for DTA. It has been shown in the above literature [32], [60]- [61]. As for ET, its effectiveness is based on similar environments or historical experiences suffered by agents.…”

Section: B Multi-agent Reinforcement Learning (Marl)mentioning

confidence: 99%

“…In this paper, we chose Sioux Falls (SF) network (see FIGURE 2) with 24 nodes and 76 edges widely used to test traffic assignment or route choice methods in the literature, such as [60], [33] and [68]. Compared to commonly adopted conceptual grid networks, which only has few OD pairs and one-way roads or paths, SF network describes a situation which is closer to the real world.…”

Section: ) Traffic Networkmentioning

confidence: 99%

“…The values of coefficient  and  are 0.15 and 4 respectively. The above calibration values are usually used in the BPR-type function that describes the travel cost of a general road, for instance, the travel cost in [71], [60], and [72].…”

Section: ) Traffic Networkmentioning

confidence: 99%

See 3 more Smart Citations

A Distributed Assignment Method for Dynamic Traffic Assignment Using Heterogeneous-Adviser Based Multi-Agent Reinforcement Learning

Pan

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The Dynamic Traffic Assignment (DTA) is one of the important measures to alleviate urban network traffic congestion. The congestions are usually caused by stochastic traffic demands, which are generally unassignable from time dimension in the real-world but are assumed to be assignable in existing DTA methods (i.e. real-time travel demands). In this paper, a distributed DTA method for preventing urban network traffic congestion caused by stochastic real-time travel demands by improving Multi-Agent Reinforcement Learning (MARL). A team structure, which consists of decision-makers and advisers, is designed to learn parallelly in realistic DTA tasks. To reduce the size of the solution space adaptively, the dynamic critical values advised by adviser agents are adopted as constraints for the strategy space of decision-makers (i.e. main agents). A collaborative heterogeneous-adviser mechanism is designed to avoid deviation of guidance. To enhance the adaptability of DTA to the changeable external environment, the mixed strategy concept is introduced to improve the decision-making process of main agents. The respective mapping mechanisms are designed to define adaptive learning rates to improve the sensitivity of MARL. The Sioux Falls (SF) network is established as a test platform via a Dynamic Network Loading (DNL). The effectiveness of the suggested DTA method is assessed through numerical simulations SF network. Under the influence of the scenario with stochastic real-time travel demands, the results show that the proposed method outperforms in terms of the throughput of the network and the individual average travel time among the overall network. Additionally, the ability of the proposed method in response to the external environment rapidly has also been demonstrated. Adopting the suggested method can improve the state of the art to assign stochastic real-time travel demands dynamically and to avoid potential traffic congestion fundamentally. INDEX TERMS dynamic traffic assignment, intelligent transportation system, multi-agent system, reinforcement learning, multi-agent reinforcement learning, numerical simulation.

show abstract

Section: B Multi-agent Reinforcement Learning (Marl)mentioning

confidence: 99%

Section: B Multi-agent Reinforcement Learning (Marl)mentioning

confidence: 99%

Section: ) Traffic Networkmentioning

confidence: 99%

Section: ) Traffic Networkmentioning

confidence: 99%

See 2 more Smart Citations

A Distributed Assignment Method for Dynamic Traffic Assignment Using Heterogeneous-Adviser Based Multi-Agent Reinforcement Learning

Pan

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A study conducted by [Bazzan and Grunitzki 2016] shows that, in an en route trip building approach, the learning rate α does not play a big role, and so a value of α = 0.5 suits our needs. As for the discount factor γ, we have performed extensive tests and found that a value of γ = 0.9 performs best.…”

Section: Ql Parametersmentioning

confidence: 99%

Accelerating Learning of Route Choices With C2I: A Preliminary Investigation

Santos¹,

Bazzan²

2020

Anais Do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2020)

View full text Add to dashboard Cite

How to choose a route that takes you from A to B? This is an issue that is turning more and more important in modern societies. One way to address this agenda is through the use of communication between the infrastructure (network), and the demand (vehicles). In this paper, we use car-to-infrastructure (C2I) communication to investigate whether the road users (agents) can accelerate their learning process regarding route choice problem, via reinforcement learning (RL). We employ a microscopic simulator in order to compare our method with two others: RL without communication and an iterative method. Experimental results show that our method outperforms both methods in terms of effectiveness and efficiency.

show abstract

Traffic Route Planning in Partially Observable Environment Using Actions Group Representation

Luo

2021

Knowledge Science, Engineering and Management

View full text Add to dashboard Cite

A multiagent reinforcement learning approach to en-route trip building

Cited by 22 publications

References 15 publications

A Distributed Assignment Method for Dynamic Traffic Assignment Using Heterogeneous-Adviser Based Multi-Agent Reinforcement Learning

A Distributed Assignment Method for Dynamic Traffic Assignment Using Heterogeneous-Adviser Based Multi-Agent Reinforcement Learning

Accelerating Learning of Route Choices With C2I: A Preliminary Investigation

Traffic Route Planning in Partially Observable Environment Using Actions Group Representation

Contact Info

Product

Resources

About