1 code implementation • 25 Mar 2024 • Yuda Song, Zehao Sun, Xuanwu Yin
Recent advancements in diffusion models have positioned them at the forefront of image generation.
1 code implementation • 14 Nov 2023 • Yifei Zhou, Ayush Sekhari, Yuda Song, Wen Sun
In this work, we propose a new hybrid RL algorithm that combines an on-policy actor-critic method with offline data.
1 code implementation • 1 Mar 2023 • Anirudh Vemula, Yuda Song, Aarti Singh, J. Andrew Bagnell, Sanjiban Choudhury
We propose a novel approach to addressing two fundamental challenges in Model-based Reinforcement Learning (MBRL): the computational expense of repeatedly finding a good policy in the learned model, and the objective mismatch between model fitting and policy computation.
no code implementations • 10 Nov 2022 • Yang Zhou, Yuda Song, Hui Qian, Xin Du
Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks.
no code implementations • 30 Oct 2022 • Chengzhuo Ni, Yuda Song, Xuezhou Zhang, Chi Jin, Mengdi Wang
To our best knowledge, this is the first sample-efficient algorithm for multi-agent general-sum Markov games that incorporates (non-linear) function approximation.
1 code implementation • 13 Oct 2022 • Yuda Song, Yifei Zhou, Ayush Sekhari, J. Andrew Bagnell, Akshay Krishnamurthy, Wen Sun
We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has access to an offline dataset and the ability to collect experience via real-world online interaction.
1 code implementation • 23 Sep 2022 • Yang Zhou, Yuda Song, Xin Du
Together with a pixel-wise discriminator and supervised loss, we can train the generator to simulate the UDC imaging degradation process.
1 code implementation • 23 Sep 2022 • Yuda Song, Yang Zhou, Hui Qian, Xin Du
Image dehazing is an active topic in low-level vision, and many image dehazing networks have been proposed with the rapid development of deep learning.
Ranked #2 on Image Dehazing on RS-Haze
1 code implementation • 29 May 2022 • Alekh Agarwal, Yuda Song, Wen Sun, Kaiwen Wang, Mengdi Wang, Xuezhou Zhang
We study the problem of representational transfer in RL, where an agent first pretrains in a number of source tasks to discover a shared representation, which is subsequently used to learn a good policy in a \emph{target task}.
1 code implementation • 8 Apr 2022 • Yuda Song, Zhuqing He, Hui Qian, Xin Du
Image dehazing is a representative low-level vision task that estimates latent haze-free images from hazy images.
Ranked #1 on Image Dehazing on RS-Haze
no code implementations • 5 Apr 2022 • Yuda Song, Ye Yuan, Wen Sun, Kris Kitani
Our theoretical analysis shows that our method is a no-regret algorithm and we provide the convergence rate in the agnostic setting.
1 code implementation • 15 Mar 2022 • Yuda Song, Hui Qian, Xin Du
The dominant image-to-image translation methods are based on fully convolutional networks, which extract and translate an image's features and then reconstruct the image.
1 code implementation • 31 Jan 2022 • Xuezhou Zhang, Yuda Song, Masatoshi Uehara, Mengdi Wang, Alekh Agarwal, Wen Sun
We present BRIEE (Block-structured Representation learning with Interleaved Explore Exploit), an algorithm for efficient reinforcement learning in Markov Decision Processes with block-structured dynamics (i. e., Block MDPs), where rich observations are generated from a set of unknown latent states.
1 code implementation • ICLR 2022 • Ye Yuan, Yuda Song, Zhengyi Luo, Wen Sun, Kris Kitani
Specifically, we learn a conditional policy that, in an episode, first applies a sequence of transform actions to modify an agent's skeletal structure and joint attributes, and then applies control actions under the new design.
1 code implementation • ICCV 2021 • Yuda Song, Hui Qian, Xin Du
To make the method more practical, we propose a well-designed enhancer that can process a 4K-resolution image over 200 FPS but surpasses the contemporaneous single style image enhancement methods in terms of PSNR, SSIM, and LPIPS.
1 code implementation • 15 Jul 2021 • Yuda Song, Wen Sun
Model-based Reinforcement Learning (RL) is a popular learning paradigm due to its potential sample efficiency compared to model-free RL.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • ICML 2020 • Yuda Song, Aditi Mavalankar, Wen Sun, Sicun Gao
The high sample complexity of reinforcement learning challenges its use in practice.