Related papers: Bayesian Critique-Tune-Based Reinforcement Learnin…

Offline reinforcement learning (RL) enables learning effective policies from fixed datasets without any environment interaction. Existing methods typically employ policy constraints to mitigate the distribution shift encountered during…

Masked Image Modeling (MIM) methods, like Masked Autoencoders (MAE), efficiently learn a rich representation of the input. However, for adapting to downstream tasks, they require a sufficient amount of labeled data since their rich features…

Adaptive traffic signal control (ATSC) is crucial in alleviating congestion, maximizing throughput and promoting sustainable mobility in ever-expanding cities. Multi-Agent Reinforcement Learning (MARL) has recently shown significant…

Traffic light control is important for reducing congestion in urban mobility systems. This paper proposes a real-time traffic light control method using deep Q learning. Our approach incorporates a reward function considering queue lengths,…

The recent advancements in cloud services, Internet of Things (IoT) and Cellular networks have made cloud computing an attractive option for intelligent traffic signal control (ITSC). Such a method significantly reduces the cost of cables,…

Previous studies that have formulated multi-agent reinforcement learning (RL) algorithms for adaptive traffic signal control have primarily used value-based RL methods. However, recent literature has shown that policy-based methods may…

Camera-based adaptive traffic signal control is inherently partially observable: detections can be missed, vehicle speeds and distances can be noisy, and a phase-change decision becomes temporally irreversible once yellow onset is…

Actor-critic algorithms address the dual goals of reinforcement learning (RL), policy evaluation and improvement via two separate function approximators. The practicality of this approach comes at the expense of training instability, caused…

Modern cities experience heavy traffic flows and congestions regularly across space and time. Monitoring traffic situations becomes an important challenge for the Traffic Control and Surveillance Systems (TCSS). In advanced TCSS, it is…

City-scale traffic signal control (TSC) involves thousands of heterogeneous intersections with varying topologies, making cooperative decision-making across intersections particularly challenging. Given the prohibitive computational cost of…

While Contrastive Learning (CL) has revolutionized self-supervised representation learning, its latent representations remain highly entangled and opaque, limiting their interpretability in safety-critical applications. We identify that a…

In an effort to overcome limitations of reward-driven feature learning in deep reinforcement learning (RL) from images, we propose decoupling representation learning from policy learning. To this end, we introduce a new unsupervised…

Automated driving at unsignalized intersections is challenging due to complex multi-vehicle interactions and the need to balance safety and efficiency. Model Predictive Control (MPC) offers structured constraint handling through…

This paper proposes a Reinforcement Learning (RL)-based control framework for position and attitude control of an Unmanned Aerial System (UAS) subjected to significant disturbance that can be associated with an uncertain trigger signal. The…

Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate annotated responses for given instructions. In this paper, we propose Critique Fine-Tuning (CFT), a method more effective than SFT for reasoning tasks.…

Effective traffic signal control (TSC) is crucial in mitigating urban congestion and reducing emissions. Recently, reinforcement learning (RL) has been the research trend for TSC. However, existing RL algorithms face several real-world…

Attention mechanisms have become integral in AI, significantly enhancing model performance and scalability by drawing inspiration from human cognition. Concurrently, the Attention Schema Theory (AST) in cognitive science posits that…

Embedding tables are usually huge in click-through rate (CTR) prediction models. To train and deploy the CTR models efficiently and economically, it is necessary to compress their embedding tables at the training stage. To this end, we…

Vision-language models (VLMs), such as CLIP, have demonstrated exceptional generalization capabilities and can quickly adapt to downstream tasks through prompt fine-tuning. Unfortunately, in classification tasks involving non-training…

In this paper, we present a state-of-the-art reinforcement learning method for autonomous driving. Our approach employs temporal difference learning in a Bayesian framework to learn vehicle control signals from sensor data. The agent has…