conqur mitigating delusional bias in deep q learning
play

ConQUR: Mitigating Delusional Bias in Deep Q-Learning DiJia (Andy) - PowerPoint PPT Presentation

Dec 05, 2023 •515 likes •856 views

ConQUR: Mitigating Delusional Bias in Deep Q-Learning DiJia (Andy) Su (Princeton) Jayden Ooi (Google) Tyler Lu (Google) Dale Schuurmans (Google) Craig Boutilier (Google) - Search:

  1. ConQUR: Mitigating Delusional Bias in Deep Q-Learning DiJia (Andy) Su (Princeton) Jayden Ooi (Google) Tyler Lu (Google) Dale Schuurmans (Google) Craig Boutilier (Google)

  2. -

  3. •

  4. ●

  10. • • • •

  11. • •

  12. • •

  13. Search: Q-Regressors P 13 Proprietary & Confidential

  14. Batch #1 - - - ……………………………………….. - ……………………………………….. P 14 Proprietary & Confidential

  15. Batch #1 Batch #1 - - Generate & fit G e n e - - r a Q Q-labels t e - l a & b - ……………………………………….. - ……………………………………….. fi e t l s - ……………………………………….. - ……………………………………….. P 15 Proprietary & Confidential

  16. Batch #1 Batch #1 - - Generate & fit G e n e - - r a Q Q-labels t e - l a & b - ……………………………………….. - ……………………………………….. fi e t l s - ……………………………………….. - ……………………………………….. P 16 Proprietary & Confidential

  17. Batch #1 Batch #1 - - Generate & fit G e n e - - r a Q Q-labels t e - l a & b - ……………………………………….. - ……………………………………….. fi e t l s - ……………………………………….. - ……………………………………….. P 17 Proprietary & Confidential

  18. Batch #1 Batch #1 G - - Generate & fit e n e r a - - Q t Q-labels e - l a & b fi e - ……………………………………….. - ……………………………………….. l t s - ……………………………………….. - ……………………………………….. Q-Label Set Q-Label Set #1 #2 P 18 Proprietary & Confidential

  19. Batch #1 Batch #1 - - - - - ……………………………………….. - ……………………………………….. - ……………………………………….. - ……………………………………….. Q-Label Set Q-Label Set #1 #2 P 19 Proprietary & Confidential

  20. Batch #1 Batch #1 - - - - - ……………………………………….. - ……………………………………….. - ……………………………………….. - ……………………………………….. Batch #2 - - - ……………………………………….. - ……………………………………….. P 20 Proprietary & Confidential

  21. Batch #1 Batch #1 - - - - - ……………………………………….. - ……………………………………….. - ……………………………………….. - ……………………………………….. Batch #2 - - - ……………………………………….. - ……………………………………….. P 21 Proprietary & Confidential

  22. Batch #1 Batch #1 - - - - - ……………………………………….. - ……………………………………….. - ……………………………………….. - ……………………………………….. Batch #2 - - - ……………………………………….. - ……………………………………….. P 22 Proprietary & Confidential

  23. ……… P 23 Proprietary & Confidential

  24. - - - -

  25. 1)

  26. λ

  27. λ

  28. • • • • -

  29. •

  30. •

  32. • • • •

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Estimating and Mitigating Gender Bias in Deep Image Representations Tianlu Wang University of

Estimating and Mitigating Gender Bias in Deep Image Representations Tianlu Wang University of

Balance ced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations Tianlu Wang University of Virginia Tianlu Wang-Gender Bias in Deep Image Representation Gender Bias in Visual Recognition Systems Deep

486 views • 36 slides
CS7015 (Deep Learning) : Lecture 8 Regularization: Bias Variance Tradeoff, l2 regularization,

CS7015 (Deep Learning) : Lecture 8 Regularization: Bias Variance Tradeoff, l2 regularization,

CS7015 (Deep Learning) : Lecture 8 Regularization: Bias Variance Tradeoff, l2 regularization, Early stopping, Dataset augmentation, Parameter sharing and tying, Injecting noise at input, Ensemble methods, Dropout Mitesh M. Khapra Department of

1.06k views • 86 slides
A short overview on Reducing model bias in a deep learning classifier using domain adversarial

A short overview on Reducing model bias in a deep learning classifier using domain adversarial

A short overview on Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERA experiment Anushree Ghosh, UTFSM, Chile Fermilab Date: 2018-11-07 1 Outline MINERvA detector and the

368 views • 25 slides
Mitigating Gender Bias Amplification in Distribution by Posterior Regularization Shengyu Jia *

Mitigating Gender Bias Amplification in Distribution by Posterior Regularization Shengyu Jia *

Mitigating Gender Bias Amplification in Distribution by Posterior Regularization Shengyu Jia * , Tao Meng * , Jieyu Zhao , Kai-Wei Chang Tsinghua University University of California, Los Angeles Credit to Mark Yatskar Credit

162 views • 13 slides
Bias Also Matters: Bias Attribution for Deep Neural Network Explanation Shengjie Wang*, Tianyi

Bias Also Matters: Bias Attribution for Deep Neural Network Explanation Shengjie Wang*, Tianyi

Bias Also Matters: Bias Attribution for Deep Neural Network Explanation Shengjie Wang*, Tianyi Zhou*, Jeff A. Bilmes University of Washington, Seattle Explain DNNs as a linear model per data point DNN with piecewise linear activations like

250 views • 9 slides
Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Deep 3D Representation Learning for Visual Computing Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms Conclusion 2 Outline Overview of 3D deep learning Background 3D deep learning tasks 3D deep

1.66k views • 122 slides
ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY MEDIA & ENTERTAINMENT SECURITY & DEFENSE AUTONOMOUS MACHINES Image

307 views • 26 slides
Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach Proteek Roy

Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach Proteek Roy

Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach Proteek Roy and Vishnu Boddeti Michigan State University CVPR 2019 [~]$ [1/13] >>> Representation Learning: The Bright Side * Deep Embeddings: E (

674 views • 39 slides
BIAS What Is Bias? Bias can be defined as favoring one side, position, or belief being

BIAS What Is Bias? Bias can be defined as favoring one side, position, or belief being

BIAS What Is Bias? Bias can be defined as favoring one side, position, or belief being partial or prejudiced Where have you seen bias? Bias vs. Propaganda Bias is prejudice; a preconceived judgment or an opinion formed

717 views • 29 slides
Bias-Variance Tradeoff Machine Learning 1 Bias and variance Every learning algorithm requires

Bias-Variance Tradeoff Machine Learning 1 Bias and variance Every learning algorithm requires

Bias-Variance Tradeoff Machine Learning 1 Bias and variance Every learning algorithm requires assumptions about the hypothesis space. Eg: My hypothesis space is linear decision trees with 5 nodes a three layer

189 views • 17 slides
Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice Scaling up DL 2 What is Deep Learning? 3 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY SECURITY & DEFENSE MEDIA &

1.45k views • 39 slides
Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning Methods) Peter Henderson Statistical Society of Canada Annual Meeting 2018 Contributors Riashat Islam Phil Bachman Doina Precup David Meger Joelle

850 views • 37 slides
Invertible Generative Models for Inverse Problems Mitigating Representation Error and Dataset Bias

Invertible Generative Models for Inverse Problems Mitigating Representation Error and Dataset Bias

Invertible Generative Models for Inverse Problems Mitigating Representation Error and Dataset Bias M. Asim, M. Daniels, O. Leong, P . Hand, A. Ahmed Inverse Problems with Generative Models as Image Priors Inverse Problems with Generative Models

369 views • 22 slides
The Bugs That Won't Go Away Your role in delusional infestation The webinar will begin promptly

The Bugs That Won't Go Away Your role in delusional infestation The webinar will begin promptly

The Bugs That Won't Go Away Your role in delusional infestation The webinar will begin promptly at 11am EDT (GMT -04:00). Please make sure your computer speakers are on. There is no call in number. Use the chat box (to everyone) for any

580 views • 25 slides
Bias Busting Across the Center: A Model to Interrupt Bias and Promote Inclusion Modeled on

Bias Busting Across the Center: A Model to Interrupt Bias and Promote Inclusion Modeled on

Bias Busting Across the Center: A Model to Interrupt Bias and Promote Inclusion Modeled on Googles BiasBusting@Work and Carnegie Mellons Bias Busters @ CMU Learning Outcomes Understand the role that biases play, positively &

637 views • 34 slides
Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI Mission Helping people solve challenging problems using AI and deep learning. Developers, data scientists and engineers Self-driving cars,

1.44k views • 72 slides
Batch-Incremental vs. Instance-Incremental Learning in Dynamic and Evolving Data Jesse Read 1 ,

Batch-Incremental vs. Instance-Incremental Learning in Dynamic and Evolving Data Jesse Read 1 ,

Batch-Incremental vs. Instance-Incremental Learning in Dynamic and Evolving Data Jesse Read 1 , Albert Bifet 2 , Bernhard Pfahringer 2 , Geoff Holmes 2 1 Department of Signal Theory and Communications Universidad Carlos III Madrid, Spain 2

568 views • 19 slides
Lecture 14: Batch RL Emma Brunskill CS234 Reinforcement Learning. Winter 2020 Slides drawn from

Lecture 14: Batch RL Emma Brunskill CS234 Reinforcement Learning. Winter 2020 Slides drawn from

Lecture 14: Batch RL Emma Brunskill CS234 Reinforcement Learning. Winter 2020 Slides drawn from Philip Thomas with modifications *Note: we only went carefully through slides before slide 34. The remaining slides are kept for those interested

1.19k views • 74 slides
The FICEP Infrastructure How We Deployed the Italian eIDAS Node in the Cloud P. Smiraglia, M. De

The FICEP Infrastructure How We Deployed the Italian eIDAS Node in the Cloud P. Smiraglia, M. De

The FICEP Infrastructure How We Deployed the Italian eIDAS Node in the Cloud P. Smiraglia, M. De Benedictis, A. Atzeni, A. Lioy and M. Pucciarelli eDemocracy 2017: December 14th, 2017 What FICEP is? First Italian Crossborder eIDAS Proxy

498 views • 17 slides
Debugging Scalable Applications on the XT May 2nd 2009 Chris Gottbrath Director, Product

Debugging Scalable Applications on the XT May 2nd 2009 Chris Gottbrath Director, Product

Debugging Scalable Applications on the XT May 2nd 2009 Chris Gottbrath Director, Product Management Debugging Scalable Applications Intro Challenges Products Scalability Interactive Subset Debugging Batch

727 views • 30 slides
Batch IS NOT Heavy: Learning Word Representations From All Samples 1 1 1 Xin Xin, Fajie Yuan,

Batch IS NOT Heavy: Learning Word Representations From All Samples 1 1 1 Xin Xin, Fajie Yuan,

Batch IS NOT Heavy: Learning Word Representations From All Samples 1 1 1 Xin Xin, Fajie Yuan, Xiangnan He, Joemon Jose 2 1 School of Computing Science, University of Glasgow 2 School of Computing, National University of Singapore Presented by

603 views • 28 slides
BATCH BINARY WEIERSTRASS ECC 2019, Bochum, Germany 02 December 2019 Billy Bob Brumley Sohaib ul

BATCH BINARY WEIERSTRASS ECC 2019, Bochum, Germany 02 December 2019 Billy Bob Brumley Sohaib ul

BATCH BINARY WEIERSTRASS ECC 2019, Bochum, Germany 02 December 2019 Billy Bob Brumley Sohaib ul Hassan Alex Shaindlin Nicola Tuveri Kide Vuojrvi Network and Information Security Group (NISEC) Tampere University, Tampere, FINLAND default

701 views • 20 slides
0 Taking a macro-step r L T ( w t ) is the same as taking the N micro-steps N r

0 Taking a macro-step r L T ( w t ) is the same as taking the N micro-steps N r

Stochastic Gradient Descent Batch Gradient Descent Cook'T I encio P N r L T ( w ) = 1 n = 1 r ` n ( w ) . N 0 Taking a macro-step r L T ( w t ) is the same as taking the N micro-steps N r ` 1 ( w t ) , . . . , N r `

465 views • 12 slides
Yeti Operations Committee MARCH 7 2016 MEETING Agenda 1. Usage Report 2. Home Directory

Yeti Operations Committee MARCH 7 2016 MEETING Agenda 1. Usage Report 2. Home Directory

Yeti Operations Committee MARCH 7 2016 MEETING Agenda 1. Usage Report 2. Home Directory Quotas 3. Other Topics 4. Executive Session 2 CoreDays - Last 12 Months 3 Jobs by Queue Type Jan-Feb 2016 Queue Total Jobs Avg. Cores Avg. Wait

420 views • 11 slides

More recommend