paper-with-me

Papers

REPAINT: Knowledge Transfer in Deep Reinforcement Learning

2020-11-24 · Yunzhe Tao, Sahika Genc, Jonathan Chung, Tao Sun, Sunil Mallya

Accelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low. This work proposes REPresentation And INstance Transfer (REPAINT) algorithm for knowledge transfer in deep reinforcement learning. REPAINT not only transfers the representation of a pre-trained teacher policy in the on-policy learning, but also uses an advantage-based experience selection approach to transfer useful samples collected following the teacher policy in the off-policy learning. Our experimental results on several benchmark tasks show that REPAINT significantly reduces the total training time in generic cases of task similarity. In particular, when the source tasks are dissimilar to, or sub-tasks of, the target tasks, REPAINT outperforms other baselines in both training-time reduction and asymptotic performance of return scores.

📄 PDF Abstract BibTeX arXiv:2011.11827

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Transfer Learning

Similar Papers 제목 키워드 기반

REPAINT: Knowledge Transfer in Deep Actor-Critic Reinforcement Learning

2020-09-28 · Yunzhe Tao, Sahika Genc, Tao Sun, Sunil Mallya

Accelerating the learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and targ…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Transfer Learning

RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning

2025-10-09 · Zipeng Guo, Lichen Ma, Xiaolong Fu, Gaojing Zhou 외 arxiv

In web data, product images are central to boosting user engagement and advertising efficacy on e-commerce platforms, yet the intrusive elements such as watermarks and promotional text remain major obstacles to deliverin…

Reinforcement Learning

A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models

2023-02-02 · Litu Rout, Advait Parulekar, Constantine Caramanis, Sanjay Shakkottai

We provide a theoretical justification for sample recovery using diffusion based image inpainting in a linear model setting. While most inpainting algorithms require retraining with each new mask, we prove that diffusion…

DenoisingImage Inpainting

Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting

2023-12-20 · Junwu Zhang, Zhenyu Tang, Yatian Pang, Xinhua Cheng 외

Recent one image to 3D generation methods commonly adopt Score Distillation Sampling (SDS). Despite the impressive results, there are multiple deficiencies including multi-view inconsistency, over-saturated and over-smoo…

3D GenerationImage GenerationImage to 3D

Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examples

2021-10-20 · Amin Banitalebi-Dehkordi, Yong Zhang

Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the `texture bias' i…

Colorizationimage-classificationImage Classificationobject-detection+1