相关论文: Score-Based One-step MeanFlow Policy Optimization

Diffusion and flow models have emerged as powerful generative approaches capable of modeling diverse and multimodal behavior. However, applying these models to offline reinforcement learning (RL) remains challenging due to the iterative…

Soft actor-critic (SAC) is a popular algorithm for max-entropy reinforcement learning. In practice, the energy-based policies in SAC are often approximated using simple policy classes for efficiency, sacrificing the expressiveness and…

Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory…

Incorporating pre-collected offline data can substantially improve the sample efficiency of reinforcement learning (RL), but its benefits can break down when the transition dynamics in the offline dataset differ from those encountered…

This work presents DCFlow, a novel unsupervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Unlike previous approaches that implicitly learn flow…

Diffusion policies have shown promise in learning complex behaviors from demonstrations, particularly for tasks requiring precise control and long-term planning. However, they face challenges in robustness when encountering distribution…

Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…

The goal of offline reinforcement learning (RL) is to find an optimal policy given prerecorded trajectories. Many current approaches customize existing off-policy RL algorithms, especially actor-critic algorithms in which policy evaluation…

The interpretation of ego motion and scene change is a fundamental task for mobile robots. Optical flow information can be employed to estimate motion in the surroundings. Recently, unsupervised optical flow estimation has become a research…

This paper introduces EnergyFlow, a framework that unifies generative action modeling with inverse reinforcement learning by parameterizing a scalar energy function whose gradient is the denoising field. We establish that under…

Speech enhancement (SE) recovers clean speech from noisy signals and is vital for applications such as telecommunications and automatic speech recognition (ASR). While generative approaches achieve strong perceptual quality, they often rely…

Generative flow and diffusion models provide the continuous, multimodal action distributions needed for high-precision robotic policies. However, their reliance on iterative sampling introduces severe inference latency, degrading control…

Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical architectures such as…

State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation.…

Policy gradient methods are an attractive approach to multi-agent reinforcement learning problems due to their convergence properties and robustness in partially observable scenarios. However, there is a significant performance gap between…

Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elaborative designs of…

Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling…

Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based…

We propose GoalFlow, an end-to-end autonomous driving method for generating high-quality multimodal trajectories. In autonomous driving scenarios, there is rarely a single suitable trajectory. Recent methods have increasingly focused on…

Traffic flow prediction is an important part of smart transportation. The goal is to predict future traffic conditions based on historical data recorded by sensors and the traffic network. As the city continues to build, parts of the…