Computer-Aided Civil and Infrastructure Engineering · 2022 · 22 citations · 46 references
EngineeringDecision SciencesMachine LearningMarkov Decision ProcessesOptimizationReinforcement LearningTraffic EngineeringTraffic Flow TheoryTraffic Signal ControlMarkov Decision ModelsMeta-reinforcement LearningReinforcement Learning For Signal ControlReinforcement Learning ModelsReinforcement Learning TheorySaturationTarget ProblemTraffic Congestion
Reinforcement learning (RL) algorithms have been widely applied in solving traffic signal control problems. Traffic environments, however, are intrinsically nonstationary, which creates a convergence problem that RL algorithms struggle to overcome. Basically, as a target problem for an RL algorithm, the Markov decision process (MDP) can be solved only when both the transition and reward functions do not vary. Unfortunately, the environment for traffic signal control is not stationary since the goal of traffic signal control varies according to congestion levels. For unsaturated traffic conditions, the objective of traffic signal control should be to minimize vehicle delay. On the other hand, the objective must be to maximize the throughput when traffic flow is saturated. A multiregime analysis is possible for varying conditions, but classifying the traffic regime creates another complex task. The present study provides a meta-RL algorithm that embeds a latent vector to recognize the different contexts of an environment in order to automatically classify traffic regimes and apply a customized reward for each context. In simulation experiments, the proposed meta-RL algorithm succeeded in differentiating rewards according to the saturation level of traffic conditions.
46
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
A survey on Image Data Augmentation for Deep Learning
Connor Shorten, Taghi M. Khoshgoftaar · Journal Of Big Data · 2019 · 12.4K citations · Full text
Soft Actor-Critic Algorithms and Applications
Tuomas Haarnoja, Aurick Zhou, Kristian Hartikainen et al. · arXiv (Cornell University) · 2018 · 2K citations · Full text