Related papers: ReconDreamer-RL: Enhancing Reinforcement Learning …

Reinforcement Learning (RL) has emerged as a dominant paradigm for end-to-end autonomous driving (AD). However, RL suffers from sample inefficiency and a lack of semantic interpretability in complex scenarios. Foundation Models,…

Deep reinforcement learning (DRL) demonstrates its potential in learning a model-free navigation policy for robot visual navigation. However, the data-demanding algorithm relies on a large number of navigation trajectories in training.…

How to explore corner cases as efficiently and thoroughly as possible has long been one of the top concerns in the context of deep reinforcement learning (DeepRL) autonomous driving. Training with simulated data is less costly and dangerous…

Realistic and interactive scene simulation is a key prerequisite for autonomous vehicle (AV) development. In this work, we present SceneDiffuser, a scene-level diffusion prior designed for traffic simulation. It offers a unified framework…

Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…

Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent…

We introduce Scenario Dreamer, a fully data-driven generative simulator for autonomous vehicle planning that generates both the initial traffic scene - comprising a lane graph and agent bounding boxes - and closed-loop agent behaviours.…

We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the…

Understanding and modeling lighting effects are fundamental tasks in computer vision and graphics. Classic physically-based rendering (PBR) accurately simulates the light transport, but relies on precise scene representations--explicit 3D…

Deep reinforcement learning (DRL) is a promising method to learn control policies for robots only from demonstration and experience. To cover the whole dynamic behaviour of the robot, DRL training is an active exploration process typically…

We study active object tracking, where a tracker takes visual observations (i.e., frame sequences) as input and produces the corresponding camera control signals as output (e.g., move forward, turn left, etc.). Conventional methods tackle…

This paper presents a novel approach for unsupervised video summarization using reinforcement learning (RL), addressing limitations like unstable adversarial training and reliance on heuristic-based reward functions. The method operates on…

Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models faces significant challenges in computational efficiency and data acquisition. We propose AcceRL, a fully asynchronous and decoupled RL framework designed to…

Reinforcement learning (RL) is playing an increasingly important role in fields such as robotic control and autonomous driving. However, the gap between simulation and the real environment remains a major obstacle to the practical…

Decision-making for urban autonomous driving is challenging due to the stochastic nature of interactive traffic participants and the complexity of road structures. Although reinforcement learning (RL)-based decision-making scheme is…

Autonomous Underwater Vehicles (AUVs) are essential for marine exploration, yet their control remains highly challenging due to nonlinear dynamics and uncertain environmental disturbances. This paper presents a diffusion-augmented…

This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provide excellent generative modeling capability, practical…

Goal-Conditioned Reinforcement Learning (GCRL) enables agents to autonomously acquire diverse behaviors, but faces major challenges in visual environments due to high-dimensional, semantically sparse observations. In the online setting,…

To safely navigate intricate real-world scenarios, autonomous vehicles must be able to adapt to diverse road conditions and anticipate future events. World model (WM) based reinforcement learning (RL) has emerged as a promising approach by…

End-to-end (E2E) autonomous driving models that take only camera images as input and directly predict a future trajectory are appealing for their computational efficiency and potential for improved generalization via unified optimization;…