Related papers: Deep Latent Competition: Learning to Race Using Vi…

We propose a new representation of visual data that disentangles object position from appearance. Our method, termed Deep Latent Particles (DLP), decomposes the visual input into low-dimensional latent ``particles'', where each particle is…

In this paper, we explore using deep reinforcement learning for problems with multiple agents. Most existing methods for deep multi-agent reinforcement learning consider only a small number of agents. When the number of agents increases,…

We introduce Learning-Augmented Control (LAC), an approach that integrates untrusted machine learning predictions into the control of constrained, nonlinear dynamical systems. LAC is designed to achieve the "best-of-both-worlds" guarantees,…

Lane change is a challenging task which requires delicate actions to ensure safety and comfort. Some recent studies have attempted to solve the lane-change control problem with Reinforcement Learning (RL), yet the action is confined to…

This paper explores the application of deep reinforcement learning (RL) techniques in the domain of autonomous self-driving car racing. Motivated by the rise of AI-driven mobility and autonomous racing events, the project aims to develop an…

Learning how to adapt to complex and dynamic environments is one of the most important factors that contribute to our intelligence. Endowing artificial agents with this ability is not a simple task, particularly in competitive scenarios. In…

Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for expensive online learning. Despite strong generalization in…

Intelligent agents need to select long sequences of actions to solve complex tasks. While humans easily break down tasks into subgoals and reach them through millions of muscle commands, current artificial intelligence is limited to tasks…

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

The increasingly complicated and diverse applications have distinct network performance demands, e.g., some desire high throughput while others require low latency. Traditional congestion controls (CC) have no perception of these demands.…

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies…

Deep reinforcement learning has achieved superhuman racing performance in high-fidelity simulators like Gran Turismo 7 (GT7). It typically utilizes global features that require instrumentation external to a car, such as precise localization…

Deep reinforcement learning is actively used for training autonomous car policies in a simulated driving environment. Due to the large availability of various reinforcement learning algorithms and the lack of their systematic comparison…

Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…

Through multi-agent competition and the sparse high-level objective of winning a race, we find that both agile flight (e.g., high-speed motion pushing the platform to its physical limits) and strategy (e.g., overtaking or blocking) emerge…

Both generative learning and discriminative learning have recently witnessed remarkable progress using Deep Neural Networks (DNNs). For structured input synthesis and structured output prediction problems (e.g., layout-to-image synthesis…

Deep Reinforcement Learning (DRL) enables robots to learn complex behaviors through interaction with the environment. However, due to the unrestricted nature of the learning algorithms, the resulting solutions are often brittle and appear…

Current face recognition tasks are usually carried out on high-quality face images, but in reality, most face images are captured under unconstrained or poor conditions, e.g., by video surveillance. Existing methods are featured by learning…

Reinforcement learning (RL) algorithms can find an optimal policy for a single agent to accomplish a particular task. However, many real-world problems require multiple agents to collaborate in order to achieve a common goal. For example, a…

Machine learning has been widely applied to various applications, some of which involve training with privacy-sensitive data. A modest number of data breaches have been studied, including credit card information in natural language data and…