Visual Transfer For Reinforcement Learning Via Wasserstein Domain Confusion

02/02/2021

Visual Transfer For Reinforcement Learning Via Wasserstein Domain Confusion

Josh Roy, George D. Konidaris

Keywords:

Abstract Paper Similar Papers

Abstract: We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a source and target task. WAPPO approximates and minimizes the Wasserstein-1 distance between the distributions of features from source and target domains via a novel Wasserstein Confusion objective. WAPPO outperforms the prior state-of-the-art in visual transfer and successfully transfers policies across Visual Cartpole and both the easy and hard settings of of 16 OpenAI Procgen environments.

The video of this talk cannot be embedded. You can watch it here:

https://slideslive.com/38949275

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

06/12/2021

Aligning Pretraining for Detection via Object-Level Contrastive Learning

Fangyun Wei, Yue Gao, Zhirong Wu and
Han Hu, Stephen Lin

Keywords Paper

vision, contrastive learning, representation learning, transfer learning

0

0

0

0

10:23

06/12/2021

Dual Progressive Prototype Network for Generalized Zero-Shot Learning

Chaoqun Wang, Shaobo Min, Xuejin Chen and
Xiaoyan Sun, Houqiang Li

Keywords Paper

0

0

0

0

10:51

06/12/2020

Variational Interaction Information Maximization for Cross-domain Disentanglement

HyeongJoo Hwang, Geon-Hyeong Kim, Seunghoon Hong, Kee-Eung Kim

Keywords Paper

Classification, Few-Shot Learning, Missing Data, Network Analysis, Adversarial Learning

0

0

0

0

3:28

06/12/2021

Self-Supervised Learning Disentangled Group Representation as Feature

Tan Wang, Zhongqi Yue, Jianqiang Huang and
Qianru Sun, Hanwang Zhang

Keywords Paper

self-supervised learning, contrastive learning

0

0

0

0

16:04

18/07/2021

Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning

Jongwook Choi, Archit Sharma, Honglak Lee and
Sergey Levine, Shixiang Gu

Keywords Paper

Neuroscience and Cognitive Science, Neuroscience, Reinforcement Learning and Planning, Algorithms, Representation Learning; Algorithms, Sparse Coding and Dimensionality Expansion; Applications, Matrix and Ten

0

0

0

0

5:16

18/07/2021

Decoupling Value and Policy for Generalization in Reinforcement Learning

Roberta Raileanu, Rob Fergus

Keywords Paper

Theory, Learning Theory, Theory, Large Deviations and Asymptotic Analysis, Reinforcement Learning and Planning, Deep RL

0

0

0

0

16:35

05/01/2021

Cross-Domain Latent Modulation for Variational Transfer Learning

Jinyong Hou, Jeremiah D. Deng, Stephen Cranefield, Xuejie Ding

Keywords Paper

0

0

0

0

4:52

22/11/2021

Multi-Source Domain Adaptation via supervised contrastive learning and confident consistency regularization

Marin Scalbert, Florent Couzinié-Devy, Maria Vakalopoulou

Keywords Paper

unsupervised domain adaptation, contrastive learning, semi-supervised learning, consistency regularization, domain shift

0

0

0

0

2:57

03/05/2021

The inductive bias of ReLU networks on orthogonally separable data

Mary Phuong, Christoph H Lampert

Keywords Paper

implicit bias, extremal sector, gradient descent, inductive bias, max-margin, ReLU networks

0

0

0

0

5:00

06/12/2020

Unsupervised Learning of Dense Visual Representations

Pedro O. Pinheiro, Amjad Almahairi, Ryan Benmalek and
Florian Golemo, Aaron Courville

Keywords Paper

0

0

0

0

3:24

14/06/2020

Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning

Byungsoo Ko, Geonmo Gu

Keywords Paper

metric learning, image retrieval, image clustering, augmentation, sample generation, hard sample mining, pair-based loss, triplet loss, n-pair loss, multi-similarity loss

0

0

0

0

1:00

06/12/2021

Object-aware Contrastive Learning for Debiased Scene Representation

Sangwoo Mo, Hyunwoo Kang, Kihyuk Sohn and
Chun-Liang Li, Jinwoo Shin

Keywords Paper

self-supervised learning, contrastive learning, representation learning

0

0

0

0

10:25

06/12/2021

Looking Beyond Single Images for Contrastive Semantic Segmentation Learning

FEIHU ZHANG, Philip Torr, Rene Ranftl, Stephan Richter

Keywords Paper

machine learning, vision, contrastive learning, representation learning

0

0

0

0

14:48

06/12/2020

Contrastive Learning with Adversarial Examples

Chih-Hui Ho, Nuno Nvasconcelos

Keywords Paper

0

0

0

0

3:13

14/06/2020

Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment

Qiuyu Chen, Wei Zhang, Ning Zhou and
Peng Lei, Yi Xu, Yu Zheng, Jianping Fan

Keywords Paper

image aesthetics assessment, kernel embedding, adaptive convolution, parameter-free, aspect ratio

0

0

0

0

1:01

26/04/2020

Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization

Michael Volpp, Lukas P. Fröhlich, Kirsten Fischer and
Andreas Doerr, Stefan Falkner, Frank Hutter, Christian Daniel

Keywords Paper

Transfer Learning, Meta Learning, Bayesian Optimization, Reinforcement Learning

0

0

0

0

5:05

26/04/2020

Dynamics-Aware Embeddings

William Whitney, Rajat Agarwal, Kyunghyun Cho, Abhinav Gupta

Keywords Paper

representation learning, reinforcement learning, rl

0

0

0

0

4:20

22/11/2021

Domain Attention Consistency for Multi-Source Domain Adaptation

Zhongying Deng, Kaiyang Zhou, Yongxin Yang, Tao Xiang

Keywords Paper

Transferable Attribute Learning, Domain Attention Consistency, Multi-Source Domain Adaptation

0

0

0

0

9:24

18/07/2021

Decoupling Representation Learning from Reinforcement Learning

Adam Stooke, Kimin Lee, Pieter Abbeel, Michael Laskin

Keywords Paper

Optimization, Submodular Optimization, Algorithms, Bandit Algorithms; Algorithms, Online Learning, Deep Learning, Embedding and Representation learning

0

0

0

0

5:15

06/12/2020

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, Geoffrey Gordon

Keywords Paper

0

0

0

0

3:19

06/12/2021

Probabilistic Attention for Interactive Segmentation

Prasad Gabbur, Manjot Bilkhu, Javier Movellan

Keywords Paper

transformers, vision

0

0

0

0

13:20

02/02/2021

Learning Intact Features by Erasing-Inpainting for Few-shot Classification

Junjie Li, Zilei Wang, Xiaoming Hu

Keywords Paper

0

0

0

0

15:15

06/12/2020

GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network

Prune Truong, Martin Danelljan, Luc V Gool, Radu Timofte

Keywords Paper

0

0

0

0

3:18

06/12/2021

Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation

Qiming Hu, Xiaojie Guo

Keywords Paper

deep learning

0

0

0

0

12:25

03/05/2021

Disentangled Recurrent Wasserstein Autoencoder

Jun Han, Martin Min, Ligong Han and
Li Erran Li, Xuan Zhang

Keywords Paper

Recurrent Generative Model, Sequential Representation Learning, Disentanglement

0

0

0

0

9:17

18/07/2021

Recomposing the Reinforcement Learning Building Blocks with Hypernetworks

Elad Sarafian, Shai Keynan, Sarit Kraus

Keywords Paper

Reinforcement Learning and Planning, Deep RL

0

0

0

0

5:16

06/12/2021

Implicit Semantic Response Alignment for Partial Domain Adaptation

Wenxiao Xiao, Zhengming Ding, Hongfu Liu

Keywords Paper

domain adaptation, transfer learning

0

0

0

0

11:43

06/12/2020

Learning Black-Box Attackers with Transferable Priors and Query Feedback

Jiancheng YANG, Yangzhou Jiang, Xiaoyang Huang and
Bingbing Ni, Chenglong Zhao

Keywords Paper

0

0

0

0

3:22

18/07/2021

Phasic Policy Gradient

Karl Cobbe, Jacob Hilton, Oleg Klimov, John Schulman

Keywords Paper

Reinforcement Learning and Planning, Deep RL

0

0

0

0

20:40

14/06/2020

Image Search With Text Feedback by Visiolinguistic Attention Learning

Yanbei Chen, Shaogang Gong, Loris Bazzani

Keywords Paper

vision and language, image search, text feedback, attention mechanism, transformer, multimodal learning, representation learning, composition, image retrieval, interactive image search

0

0

0

0

1:00

02/02/2021

Harmonized Dense Knowledge Distillation Training for Multi-Exit Architectures

Xinglu Wang, Yingming Li

Keywords Paper

0

0

0

0

15:12

14/06/2020

Learning to See Through Obstructions

Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang and
Yung-Yu Chuang, Jia-Bin Huang

Keywords Paper

reflection removal, fence removal, optical flow, coarse-to-fine, multiple images, computational photography, deep learning, convolutional neural network, computer vision

0

0

0

0

1:01

14/06/2020

Learning Fused Pixel and Feature-Based View Reconstructions for Light Fields

Jinglei Shi, Xiaoran Jiang, Christine Guillemot

Keywords Paper

light field, view synthesis, feature-based reconstruction, pixel-based reconstruction, deep learning, angular super-resolution

0

0

0

0

4:56

30/11/2020

MIX'EM: Unsupervised Image Classification using a Mixture of Embeddings

Ali Varamesh, Tinne Tuytelaars

Keywords Paper

0

0

0

0

6:40

23/08/2020

Feature-induced manifold disambiguation for multi-view partial multi-label learning

Jing-Han Wu, Xuan Wu, Qing-Guo Chen and
Yao Hu, Min-Ling Zhang

Keywords Paper

multi-view, disambiguation, partial label learning, multi-label learning

0

0

0

0

15:00

06/12/2021

Towards Context-Agnostic Learning Using Synthetic Data

Charles Jin, Martin Rinard

Keywords Paper

machine learning, vision

0

0

0

0

14:20

03/05/2021

Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning

Rishabh Agarwal, Marlos C. Machado, Pablo Samuel Castro, Marc G Bellemare

Keywords Paper

Representation Learning, Generalization, Bisimulation, Reinforcement, Contrastive learning

0

0

0

0

15:14

12/07/2020

Representation Learning via Adversarially-Contrastive Optimal Transport

Anoop Cherian, Shuchin Aeron

Keywords Paper

Representation Learning

0

0

0

0

14:47

14/06/2020

Mixture Dense Regression for Object Detection and Human Pose Estimation

Ali Varamesh, Tinne Tuytelaars

Keywords Paper

object detection, human pose estimation, mixture model, spatial regression, mixture density networks, mdn, multi-scale, dense prediction, bottom-up model

0

0

0

0

1:01

06/12/2021

HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning

Shiming Chen, Guosen Xie, Yang Liu and
Qinmu Peng, Baigui Sun, Hao Li, Xinge You, Ling Shao

Keywords Paper

generative model, domain adaptation

0

0

0

0

9:19