[HTML][HTML] Leveraging reinforcement learning for dynamic traffic control: A survey and challenges for field implementation
In recent years, the advancement of artificial intelligence techniques has led to significant
interest in reinforcement learning (RL) within the traffic and transportation community …
interest in reinforcement learning (RL) within the traffic and transportation community …
Antifragility in complex dynamical systems
Antifragility characterizes the benefit of a dynamical system derived from the variability in
environmental perturbations. Antifragility carries a precise definition that quantifies a …
environmental perturbations. Antifragility carries a precise definition that quantifies a …
[HTML][HTML] Regional route guidance with realistic compliance patterns: Application of deep reinforcement learning and MPC
Solving link-based route guidance problems for large-scale networks is computationally
challenging and faces practical issues, such as spatial–temporal data coverage. Thus …
challenging and faces practical issues, such as spatial–temporal data coverage. Thus …
N-MP: A network-state-based Max Pressure algorithm incorporating regional perimeter control
Abstract The Max Pressure (MP) framework has been shown to be an effective real-time
decentralized traffic signal control algorithm. However, despite its superior performance and …
decentralized traffic signal control algorithm. However, despite its superior performance and …
[HTML][HTML] An MFD approach to route guidance with consideration of fairness
This paper introduces two fair and efficient route guidance (RG) advisory control schemes
for proactive control of a large-size urban network. The two developed fairness-centered …
for proactive control of a large-size urban network. The two developed fairness-centered …
Perimeter control with heterogeneous metering rates for cordon signals: A physics-regularized multi-agent reinforcement learning approach
Perimeter Control (PC) strategies have been proposed to address urban road network
control in oversaturated situations by regulating the transfer flow of the Protected Network …
control in oversaturated situations by regulating the transfer flow of the Protected Network …
Optimizing gate control coordination signal for urban traffic network boundaries using multi-agent deep reinforcement learning
L Kang, H Huang, W Lu, L Liu - Expert Systems with Applications, 2024 - Elsevier
The macro-aggregated dynamic characteristics of urban network traffic flow encapsulated
embodied in macroscopic fundamental diagram theory provide a concise perspective for …
embodied in macroscopic fundamental diagram theory provide a concise perspective for …
Beyond centralization: Non-cooperative perimeter control with extended mean-field reinforcement learning in urban road networks
Perimeter control is a traffic management approach aimed at regulating vehicular
accumulation within urban regional networks by managing flows on all border-crossing …
accumulation within urban regional networks by managing flows on all border-crossing …
Hypercongestion, autonomous vehicles, and urban spatial structure
T Dantsuji, Y Takayama - Transportation Science, 2024 - pubsonline.informs.org
This paper examines the effects of hypercongestion mitigation by perimeter control and the
introduction of autonomous vehicles on the spatial structures of cities. By incorporating a …
introduction of autonomous vehicles on the spatial structures of cities. By incorporating a …
Credit assignment in heterogeneous multi-agent reinforcement learning for fully cooperative tasks
Credit assignment poses a significant challenge in heterogeneous multi-agent
reinforcement learning (MARL) when tackling fully cooperative tasks. Existing MARL …
reinforcement learning (MARL) when tackling fully cooperative tasks. Existing MARL …