Search Results for author:
Found 17 papers, 13 papers with code
SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
Recent advancements in diffusion models have positioned them at the forefront of image generation.
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
In this work, we propose a new hybrid RL algorithm that combines an on-policy actor-critic method with offline data.
The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
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.
ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning
Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks.
Representation Learning for General-sum Low-rank Markov Games
To our best knowledge, this is the first sample-efficient algorithm for multi-agent general-sum Markov games that incorporates (non-linear) function approximation.
Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
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.
Modular Degradation Simulation and Restoration for Under-Display Camera
Together with a pixel-wise discriminator and supervised loss, we can train the generator to simulate the UDC imaging degradation process.
Rethinking Performance Gains in Image Dehazing Networks
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
Provable Benefits of Representational Transfer in Reinforcement Learning
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}.
Vision Transformers for Single Image Dehazing
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
Online No-regret Model-Based Meta RL for Personalized Navigation
Our theoretical analysis shows that our method is a no-regret algorithm and we provide the convergence rate in the agnostic setting.
Multi-Curve Translator for High-Resolution Photorealistic Image Translation
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.
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach
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.
Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
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.
StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement
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.
PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration
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
Provably Efficient Model-based Policy Adaptation
The high sample complexity of reinforcement learning challenges its use in practice.
