Pieter Abbeel @pabbeel Twitter profile | Pikagi

Pikagi

Pieter Abbeel

@pabbeel

78,766

Followers

435

Following

342

Media

2,497

Statuses

Diffusion Models; Large World Model; UniSim; TRPO; SAC; Ring Attention; MAML; HER; Domain Randomization; Decision Transformer; LLM as Zero-Shot Planners; RFM-1

Berkeley, CA

https://t.co/xKkTisbJYJ

Joined August 2010

Don't wanna be here? Send us removal request.

Pinned Tweet

@pabbeel

Pieter Abbeel

2 months

Yes, 2024 is shaping up a big year for robotics! Introducing @CovariantAI 's RFM-1, which just like Sora can generate video, but RFM-1 does it for robotic interaction with the world. But there is so much more it can do. RFM-1 is a multimodal any-to-any sequence model. RFM-1

24

159

786

Last Seen Profiles

@BillyBassHarri1

@gavintrollope

@HofLab

@CAS9YGrWTcSBeil

@stw_pdg

@DasiGulabo

@Jhnmtw

@AbdulQadoo34654

@HarloChronic

@ekologebuilds

@Felix10111061

@SRHH1985

@ZooM_04

@defitaintann

@akula_srivani

@MaidanaDaniela_

@MeetWhale

@revolve2solve

@leoliverz

@Magicbullcrypto

@jandakembangstw

@RenoirAbadie

@andopile

@real_warri75830

@madak0x

@MetaX_Social

@LOYALTYGLO63030

@policingblack

@biotechinvstr

@ognek0

@MainFk8

@envozalta_libro

@Stphanseb1

@PoliceAwam

@ddyissuesgirl

@0493n

@pabbeel

Pieter Abbeel

5 years

Thrilled to be teaching a new course on Deep Unsupervised Learning with @peterxichen (ImprovedGAN, InfoGAN, PixelCNN++, VLAE, PixelSNAIL, Flow++), @hojonathanho (Flow++, GAIL), @aravind7694 (Flow++). Follow along here: Lecture vids go up once captioned

Tweet media one

18

530

2K

@pabbeel

Pieter Abbeel

3 years

Very excited to share the launch of my new podcast, The Robot Brains. The first episode was just released. My first guest is brilliant AI researcher, educator, and Director of AI and Autopilot Vision at Tesla @karpathy !

35

289

1K

@pabbeel

Pieter Abbeel

4 years

Want to learn some modern robotics? All lecture videos from CS287 Advanced Robotics Fall'19 offering are now available online.

Tweet media one

14

388

1K

@pabbeel

Pieter Abbeel

4 years

Want to learn more about GAN, DC GAN, ImprovedGAN, WGAN, WGAN-GP, Progr.GAN, SN-GAN, SAGAN, BigGAN(-Deep), StyleGAN-v1,2, VIB-GAN, GANs as Energy Models? Vid: Slides: Colab: w/ @Aravind7694 @alexlioralexli

Lecture 5 and 6 Implicit Models -- GANs.pdf

drive.google.com

5

334

1K

@pabbeel

Pieter Abbeel

5 years

Looking to study more AI in 2019? All materials of our Fall offering of CS188 Artificial Intelligence are now available here: @berkeley_ai @UCBerkeley

10

351

1K

@pabbeel

Pieter Abbeel

4 years

Congatulations @karpathy !!!! Teaching the world Deep Learning, Pioneering Image Captioning w/ @drfeifei , Founding @OpenAI , Pioneering AI Self-Driving at @Tesla w/ @elonmusk . What a career already, and you have only just gotten started!! cc @techreview

Tweet card media

Andrej Karpathy

Getting computers to see—to actually see—has been an ambition of countless computer scientists for decades. Few have come closer than Andrej Karpathy, whose approach to deep neural networks allows...

www.technologyreview.com

11

100

1K

@pabbeel

Pieter Abbeel

2 years

I couldn't be more honored. So thankful for all my amazing collaborators that made this possible, my students and colleagues at @UCBerkeley , collaborators at @OpenAI and @CovariantAI , and of course my MS and PhD advisors @DaphneKoller and @AndrewYNg , where my AI journey started.

@TheOfficialACM

Association for Computing Machinery

@TheOfficialACM

2 years

Our warmest congratulations to Pieter Abbeel @pabbeel , recipient of the 2021 #ACMPrize for contributions to robot learning, including learning from demonstrations and deep reinforcement learning for robotic control. Learn more about Abbeel’s work here:

Tweet media one

30

51

429

74

42

1K

@pabbeel

Pieter Abbeel

5 years

All materials of @berkeley_ai Deep Unsupervised Learning now up: Great semester w/ @peterxichen , @Aravind7694 , @hojonathanho , and guest inst. @AlecRad , @ilyasut ,A Efros, @avdnoord Covers: AR / PixelCNN, Flow models, VAE, GAN, self-supervised learning, etc...

Tweet card media

CS294-158-SP19 Deep Unsupervised Learning Spring 2019

About: This course will cover two areas of deep learning in which labeled data is not required: Deep Generative Models and Self-supervised Learning. Recent advances in generative models have made it...

sites.google.com

15

331

1K

@pabbeel

Pieter Abbeel

3 years

Excited to share a 6-lecture series on Foundations of Deep RL: MDP basics, value & policy iteration, max-ent, DQN, policy gradient, TRPO, PPO, DDPG, SAC, model-based RL. And went in rabbit hole of fixing captions, way too much time, but enjoy the read 😅

Tweet card media

Foundations of Deep RL -- 6-lecture series by Pieter Abbeel

www.youtube.com

17

215

1K

@pabbeel

Pieter Abbeel

3 years

Very honored to share that I am the 2022 recipient of the prestigious @IEEEorg Kiyo Tomiyasu Award. A big thank you to all my collaborators, mentors, and nominators/letter writers! (all 2022 IEEE Technical Field Award winners listed here: )

Tweet media one

48

38

891

@pabbeel

Pieter Abbeel

4 years

One of my favorites from most recent offering of CS287 Advanced Robotics? Exam study handout summarizing all the main math in ~20pp. Incl. MaxEnt RL, CEM, LQR, Penalty Method, RRTs, Particle Filters, Policy Gradient, TRPO, PPO, Q-learning, DDPG, SAC,

2

174

879

@pabbeel

Pieter Abbeel

4 years

Been looking to learn about CBOW, Glove, Word2Vec, Elmo, GPT, BERT, RoBERTa, ELECTRA, T5, GPT2, and, more generally, learning language models? Here is a wonderful lecture by @OpenAI 's @AlecRad covering all of these, and more:

Tweet card media

L11 Language Models -- guest instructor: Alec Radford (OpenAI) ---...

Course homepage:https://sites.google.com/view/berkeley-cs294-158-sp20/homeLecture Instructor: Alec Radford (OpenAI)Course Instructors: Pieter Abbeel, Aravind...

www.youtube.com

3

219

854

@pabbeel

Pieter Abbeel

4 years

Very excited to share we have now packaged our Full Stack Deep Learning Bootcamp materials into a (free) online course!

@josh_tobin_

Josh Tobin

4 years

What makes production ML hard? - Cleaning, labeling, and augmenting data - Troubleshooting training and ensuring reproducibility - Deploying models and monitoring their real-world impact To help, we're excited to announce our online production ML course:

34

610

2K

10

141

743

@pabbeel

Pieter Abbeel

4 years

Been wanting to learn about CPC, CPC-v2, MoCo, SimCLR, MoCo-v2, and other self-supervised learning techniques? Wonderful lecture by @Aravind7694 for the @UCBerkeley Deep Unsupervised Learning class:

Tweet card media

Lecture 7 Self-Supervised Learning -- UC Berkeley Spring 2020 -...

Course homepage:https://sites.google.com/view/berkeley-cs294-158-sp20/homeLecture Instructor: Aravind SrinivasCourse Instructors: Pieter Abbeel, Aravind Srin...

www.youtube.com

2

162

731

@pabbeel

Pieter Abbeel

7 years

Deep RL Bootcamp lecture videos and labs release ! :) [Organized by @pabbeel , Peter Chen, Rocky Duan, @karpathy ]

Deep RL Bootcamp - Lectures

Lectures

sites.google.com

15

312

696

@pabbeel

Pieter Abbeel

2 years

Exciting announcement: in my @therobotbrains conversation with @geoffreyhinton (yes!!!!!!!!!), there will be some time for (prepared) audience questions. By Tuesday, post/like questions you have for Geoff in reply to this tweet, and I'll try to incorporate into our conversation.

Tweet media one

61

46

574

@pabbeel

Pieter Abbeel

6 months

. @nvidia Jensen Huang has always been a big supporter of the research we do at Berkeley AI Research lab and also back when we were at OpenAI. It was really nice to now get to show him at @CovariantAI what our Robotics Foundation models are starting to enable in the real world!

Tweet media one

6

39

556

@pabbeel

Pieter Abbeel

2 years

Chatting with @geoffreyhinton was really inspiring, so excited to get to share our conversation: Apple: Spotify: Google: Youtube:

Tweet card media

Season 2 Ep 22 Geoff Hinton on revolutionizing artificial intellige...

Over the past ten years, AI has experienced breakthrough after breakthrough in everything from computer vision to speech recognition, protein folding predict...

www.youtube.com

19

114

533

@pabbeel

Pieter Abbeel

6 years

My slides from today's Reinforcement Learning in AI event at Stanford: . Includes a bunch of pointers on getting started towards the end. Thanks @AndrewYNg for organizing, and was a fun panel together with Sergey Levine and @tydsh

Tweet card media

2018_03_xx__Stanford-RL-event.pdf

Shared with Dropbox

www.dropbox.com

3

167

522

@pabbeel

Pieter Abbeel

6 years

All my #NIPS2017 slides in one place! Keynote main conf: Meta-learning symp: Robot Learning ws: Learning in Transportation ws: [w/Greg Kahn] Hierarchical RL ws:

Tweet card media

2017_12_xx_NIPS-HRL-workshop-final.pdf

Shared with Dropbox

www.dropbox.com

6

168

521

@pabbeel

Pieter Abbeel

4 years

Last semester, a guest lecture fell through last minute. So improvised a lecture on the backstories behind some research papers -- i.e. not about the research results, but about how we ended up doing research in that direction. #metaresearch Online now:

Tweet card media

Lecture 24 Backstories behind how various papers came about

Instructor: Pieter AbbeelCourse Website: https://people.eecs.berkeley.edu/~pabbeel/cs287-fa19/

www.youtube.com

1

91

506

@pabbeel

Pieter Abbeel

5 years

Want to AutoAugment w/o original Google paper's budget to spend? Population-based Augmentation matches the performance -- with 1000x less compute! :) BLOG: PAPER: w/ @peterxichen , Daniel Ho, Eric Liang, Ion Stoica, R Liaw

1000x Faster Data Augmentation

The BAIR Blog

bair.berkeley.edu

1

138

498

@pabbeel

Pieter Abbeel

6 years

Thanks to everyone who made it to my talk today! Here are the slides: . #nips2017

Tweet card media

2017_12_xx_NIPS-keynote-final.pdf

Shared with Dropbox

www.dropbox.com

5

150

487

@pabbeel

Pieter Abbeel

4 years

Been looking to learn about self-supervised learning--denoising AE, context encoders*, rotation prediction*, jigsaw, CPC, MoCo, SimCLR*? Colab with tutorial-demos* now released: (by @WilsonYan8 ) Full lecture: (by @Aravind7694 )

Tweet card media

Lecture 7 Self-Supervised Learning -- UC Berkeley Spring 2020 -...

Course homepage:https://sites.google.com/view/berkeley-cs294-158-sp20/homeLecture Instructor: Aravind SrinivasCourse Instructors: Pieter Abbeel, Aravind Srin...

www.youtube.com

4

144

483

@pabbeel

Pieter Abbeel

5 years

The Full Stack Deep Learning Bootcamp was a lot of fun in person, but of course not everyone can make it in person. Very excited to start releasing the materials today, here: Happy learning from home! -- @pabbeel @josh_tobin_ @sergeykarayev w/ @l2k

12

137

476

@pabbeel

Pieter Abbeel

5 years

Video lectures of Day 2 of now posted! Includes Troubleshooting, Testing and Deployment, Research Directions, and guest lectures by @jeremyphoward and @RichardSocher !

6

118

474

@pabbeel

Pieter Abbeel

6 years

Very excited to announce something we’ve been working on for a while now: 3-day bootcamp! Instructors: @sergeykarayev ( @gradescope ), @josh_tobin_ (Berkeley/OpenAI), @karpathy (Tesla), Jai Ranganathan (Uber), Yangqing Jia (FB), @l2k ( @weightsb ), @pabbeel

Tweet card media

News, community, and courses for people building AI-powered products.

fullstackdeeplearning.com

14

121

478

@pabbeel

Pieter Abbeel

4 years

Been looking to learn about flow models? Full package released: - lecture: - slides: - lecture colab: - homework: w/Alex Li, Wilson Yan, @Aravind7694 , @peterxichen , @hojonathanho

Lecture 3 Flow Models.pdf

drive.google.com

4

100

474

@pabbeel

Pieter Abbeel

3 years

Very excited to start offering Full Stack Deep Learning as a formal course at Berkeley this Spring, while also allowing anyone outside of Berkeley to learn along! If you want to follow along, sign up for updates below! w/ @sergeykarayev & @josh_tobin_

@full_stack_dl

The Full Stack

3 years

1/ FSDL helps you turn ML experiments into shipped products with real-world impact. This Spring, @josh_tobin_ @sergeykarayev & @pabbeel are teaching an improved version as an official Berkeley course: Want to follow along as we post lectures publicly?👇

2

41

253

4

85

470

@pabbeel

Pieter Abbeel

6 years

ICLR accepted paper analysis by Arthur Pajot. Berkeley coming in second after Google, followed by Stanford, CMU, Facebook, Microsoft, Oxford, IBM, Toronto, ETH, MIT, ... Many other breakdowns, too + code

Tweet media one

7

182

463

@pabbeel

Pieter Abbeel

6 years

Video of my keynote on Deep Learning and Robotics is now available here: (includes lots of meta-learning :) . #NIPS2017

1

161

461

@pabbeel

Pieter Abbeel

3 months

Gave a lecture on Diffusion Models yesterday with @wilson1yan and @kvfrans Thanks to it being Lecture 6 into the semester (rather than Lecture 1), we could even include Sora, Mobile Diffusion, SDXL-Lightning :)

Tweet card media

L6 Diffusion Models (SP24)

CS294-158 Deep Unsupervised LearningBerkeley, Spring 2024Instructors: Pieter Abbeel, Kevin Frans, Philipp Wu, Wilson Yanhttps://sites.google.com/view/berkele...

www.youtube.com

9

69

452

@pabbeel

Pieter Abbeel

4 years

Just released Colab accompanying the lecture on Autoregressive Models: Contains 9 demos/code (see image), including MADE,WaveNet,regular/GrayScale/Parallel PixelCNN All code by Wilson Yan! Full course here:

Tweet media one

0

111

444

@pabbeel

Pieter Abbeel

6 years

Beautiful resource off @goodfellow_ian 's website I just learned about today: So many great presentations, wonderful to learn from, thanks Ian!

0

106

432

@pabbeel

Pieter Abbeel

5 years

My slides from this morning's keynote at #GTC19 . Covered: - Few-Shot Reinforcement Learning - Leveraging Simulation - Model-based RL - Learning Representations for Exploration - Few-Shot Imitation Learning

Tweet card media

2019_03_20_GTC -- Deep Learning and Robotics -- Abbeel.pdf

Shared with Dropbox

www.dropbox.com

2

107

418

@pabbeel

Pieter Abbeel

5 years

69 = number of invited talks in 2018. Most of these were tailored to specific private, non-technical audiences (so I haven't publicly shared those slides as I have often done for my technical talks), but had some extra time today to clean up:

Tweet card media

2018_12_xx_Abbeel--AI.pdf

Shared with Dropbox

www.dropbox.com

8

73

411

@pabbeel

Pieter Abbeel

4 years

Teaching Deep Unsupervised Learning (2nd edition) at @UCBerkeley this semester. You can follow along here: Instructor Team: @peterxichen , @Aravind7694 , @hojonathanho , Wilson Yan, Alex Li, @pabbeel YouTube, PDF, and Google Slides for ease of re-use

Tweet media one

0

118

408

@pabbeel

Pieter Abbeel

2 years

From 5 years ago, still very relevant today:

Tweet media one

2

55

409

@pabbeel

Pieter Abbeel

7 years

Slides from my lecture today at CIFAR RL summer school:

Tweet media one

2

150

390

@pabbeel

Pieter Abbeel

4 years

Very excited to share the news of our 40MM B-round led by @IndexVentures w/AI focused @radicalvcfund +existing investor @AmplifyPartners ! In times when supply chain resilience/robustness couldn't be any more important, excited to take the next steps in the AI Robotics journey!

@CovariantAI

Covariant

4 years

We’ve raised $40m in Series B funding led by @IndexVentures w/ AI-focused @Radicalvcfund + existing investor @AmplifyPartners . Grateful for the support of our investors, customers + partners as we continue to bring AI Robotics to the real world!

5

28

250

18

31

378

@pabbeel

Pieter Abbeel

5 years

SO EXCITED to share that @getonyxfit has publicly launched! 🎉 Everyone who has spent time in my lab, knows how much importance I put on exercise, and not just for myself :) Check it out! Congrats to @asafagus @_jamessha !! Honored to be small contributor to the Onyx team :)

6

62

380

@pabbeel

Pieter Abbeel

3 years

Excited to share the epic Season 1 finale of @therobotbrains with the amazing @ilyasut Co-Founder/Chief Scientist @OpenAI ! His breakthroughs include AlexNet, seq2seq, MT, GPT, CLIP, DallE,Codex. "According to my parents, I've been talking about AI at a relatively early age" 😂

Tweet media one

5

51

370

@pabbeel

Pieter Abbeel

5 years

Wonderful visit to NYU yesterday! Talk slides: Also lucky timing I was there same day as @ylecun 's Turing Award celebration! There was more than one cherry on the Le Cake :)

Tweet media one

2

25

363

@pabbeel

Pieter Abbeel

5 years

Deep Q learning requires many tricks to not diverge. We build on studies of stable (linear) function appr. (Gordon95: , Tsitsiklis,van Roy97: ) through contractions, and extend to NNs + new, stabler "preQN"

Tweet media one

2

89

364

@pabbeel

Pieter Abbeel

3 years

Very excited to share my CVPR keynote from this past week: I share my thoughts on how we might be able to achieve large pre-trained neural networks for robotics, hopefully getting us towards much the way pre-trained models like GPT-x/BERT in NLP.

3

57

360

@pabbeel

Pieter Abbeel

5 years

What an exciting day! Got to personally brief His Majesty, King Philippe of Belgium on Artificial Intelligence. So genuinely kind and thoughtful. And so engaged in our discussion! Can't share pictures from inside, but beautiful palace, and me in a suit! :)

Tweet media one

Tweet media two

Tweet media three

5

9

355

@pabbeel

Pieter Abbeel

5 years

Recently been spending a lot of time on sharing AI advances and trends with general audiences. Got a video recording of one of the sessions!

Tweet card media

2019-05-03 Pieter Abbeel ODSC Keynote: Recent Advances and Trends in...

Recent advances in Artificial Intelligence have enabled a wide range of breakthroughs in many domains, including image recognition, speech recognition, machi...

www.youtube.com

3

85

346

@pabbeel

Pieter Abbeel

4 years

Been looking to learn more about Semi-Supervised Learning or Unsupervised Distribution Alignment? One hour tutorials, respectively by @Aravind7694 and @peterxichen , for CS294-158:

Tweet card media

L9 Semi-Supervised Learning and Unsupervised Distribution Alignment...

Course homepage:https://sites.google.com/view/berkeley-cs294-158-sp20/homeLecture Instructors: Aravind Srinivas, Peter ChenCourse Instructors: Pieter Abbeel,...

www.youtube.com

0

69

344

@pabbeel

Pieter Abbeel

3 years

Some big news today: we / @CovariantAI raised 80MM C-round, led by @IndexVentures , and bringing in several new investors! So much exciting AI Robotics work ahead of us :)

Tweet card media

Robotic AI firm Covariant raises another $80 million | TechCrunch

In May of last year, Covariant announced that it had raised a $40 million Series B. It was a healthy sum of money for the young company, bringing its

22

21

339

@pabbeel

Pieter Abbeel

3 years

I believe ultimately most of the challenges towards value creation will be in the AI. But setting that aside, what's the hardest R&D ahead for hardware? I am gonna say "human-level hands". But I think it's feasible, and I for one can't wait to get to work with some of those

Tweet media one

22

30

336

@pabbeel

Pieter Abbeel

5 years

Want to take your Deep Learning to next level w/real-world deployment in mind? Excited to announce Edition 3 of the Full Stack Deep Learning bootcamp! Keynotes: Franziska Bell @l2k @chipro @xamat Tutorials: @pabbeel @sergeykarayev @josh_tobin_

Tweet media one

7

65

319

@pabbeel

Pieter Abbeel

5 years

Video of Lecture 1 of CS294-158 Deep Unsupervised Learning has been released We cover: - Course Logistics - Motivation - Autoregressive Models: MADE, Wavenet, PixelCNN(++), pixelsnail (self-attention) Slides on website

Tweet card media

Week 1 CS294-158 Deep Unsupervised Learning (1/30/19)

UC Berkeley CS294-158 Deep Unsupervised Learning Week 1Instructors: Pieter Abbeel, Peter Chen, Jonathan Ho, Aravind Srinivashttps://sites.google.com/view/ber...

www.youtube.com

5

73

320

@pabbeel

Pieter Abbeel

7 years

Slide-deck from NIPS Deep Reinforcement Learning via Policy Optimization tutorial by John Schulman and myself:

Tweet media one

4

148

316

@pabbeel

Pieter Abbeel

6 years

We release ProMP: Proximal Meta-Policy Search. Builds on MAML, E-MAML, DiCE, includes code for all. Code: Docs: . Paper: with Jonas Rothfuss, Dennis Lee, Ignasi Clavera, Tamim Asfour

Tweet media one

3

80

309

@pabbeel

Pieter Abbeel

6 years

Model-based RL, while sample-efficient, often doesn't match performance of model-free RL. Model-based RL via Meta-Policy Optimization resolves this by meta-RL on an ensemble of learned models. w/ I Clavera, J Ruthfuss, J Schulman, Y Fujita, A Tasfour

Tweet card media

Model-Based Reinforcement Learning via Meta-Policy Optimization

Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics,...

1

80

299

@pabbeel

Pieter Abbeel

3 years

Ep.3 of The Robot Brains Podcast is now live! I was fortunate enough to sit down with @ylecun . Yann is professor at NYU, Chief AI Scientist at Facebook, winner of the Turing Award (aka Nobel Prize of Computer Science).

Tweet media one

7

49

297

@pabbeel

Pieter Abbeel

19 days

A fun short lecture on parallelization for training large models: by @wilson1yan and @haoliuhl

Tweet card media

L12b Parallelization -- Instructor: Wilson Yan

CS294-158 Deep Unsupervised LearningUC Berkeley Spring 2024Instructors: Pieter Abbeel, Kevin Frans, Philipp Wu, Wilson Yanslides: https://drive.google.com/fi...

www.youtube.com

2

63

305

@pabbeel

Pieter Abbeel

2 years

Re-reading #geniusmakers in preparation for the Season 2 finale guest of @therobotbrains

Tweet media one

5

29

292

@pabbeel

Pieter Abbeel

9 months

Hard to imagine a better way for me to flash right back into @OpenAI early days 2016, inspiring clarity of thinking and communication by @ilyasut

Tweet card media

An Observation on Generalization

Ilya Sutskever (OpenAI)https://simons.berkeley.edu/talks/ilya-sutskever-openai-2023-08-14Large Language Models and Transformers

www.youtube.com

7

37

293

@pabbeel

Pieter Abbeel

4 years

Distinct memory from first edition of Deep RL workshop, back in 2015: room so overcrowded the security guard couldn't let Rich Sutton in... This time, our room (West Exh. Hall C) should have space for everyone! :) #NeurIPS2019

@pabbeel

Pieter Abbeel

8 years

Deep Reinforcement Learning NIPS workshop so overcrowded that the security guard decided to keep out Rich Sutton!

Tweet media one

3

48

205

1

30

295

@pabbeel

Pieter Abbeel

1 year

Super-excited to kick off S3 of @therobotbrains podcast with Yoshua Bengio. We discuss LLMs, Higher-Level Cognition, Causality, GFlow Nets, Responsible AI, Human Creativity.

Tweet card media

S3 E1 Turing Award Winner Yoshua Bengio: Equipping AI with Higher...

S3 E1: Equipping AI with Higher Level Cognition and Creativity -- Guest: Turing Award Winner Yoshua Bengio (Host: Pieter Abbeel)What's in this episode: 00:0...

www.youtube.com

12

54

286

@pabbeel

Pieter Abbeel

4 years

Very excited about the @NeurIPSConf 2020 Deep RL Workshop! Amazing line-up of invited speakers: @marcgbellemare Matt Botvinick @RealAshEdwards Karen Liu @SusanMurphylab1 Anusha Nagabandi @pyoudeyer Peter Stone Paper submission deadline: Oct 5, 2020

Tweet media one

2

62

284

@pabbeel

Pieter Abbeel

6 years

Amazing, very accessible CS Theory talk series I just found out about today. Videos of all lectures available. Just watched Scott Aaronson and Mary Wootters' talks.

0

67

281

@pabbeel

Pieter Abbeel

7 years

Robot: (1) watch, (2) similar task, (3) hallucinate success, (4) RL to success. by Y Liu*,A Gupta*,P Abbeel,S Levine

3

108

273

@pabbeel

Pieter Abbeel

4 years

Want to catch up on some latest Deep RL work? Here is a zip file with all the camera-ready papers from the #NeurIPS2019 Deep RL Workshop!

all-papers-deep-rl-workshop-2019.zip

drive.google.com

4

72

269

@pabbeel

Pieter Abbeel

2 years

Kenji Doya reminded us of the neuroscience version of @ylecun 's LeCake at this year's Deep RL workshop.

Tweet media one

0

66

269

@pabbeel

Pieter Abbeel

4 years

Want to learn more about compression and the role of generative models? Covers: Kraft-McMillan, Shannon, Huffman, Arithmetic Coding, Asymmetric Numeral Systems (ANS), Bits-Back, coding with Autoregressive, VAE, Flow models

Tweet card media

L10 Compression -- UC Berkeley, Spring 2020, CS294-158 Deep Unsuper...

Course homepage:https://sites.google.com/view/berkeley-cs294-158-sp20/homeLecture Instructors: Pieter Abbeel, Jonathan HoCourse Instructors: Pieter Abbeel, A...

www.youtube.com

2

57

260

@pabbeel

Pieter Abbeel

4 years

love this video of Jennifer @doudna_lab recorded this morning upon notification of her Nobel Prize (for CRISPR). Looks such an awesome lab to part of!

Tweet card media

First Day in a Nobel Life: Jennifer Doudna

October 7, 2020 - Scenes from the day that UC Berkeley Professor Jennifer Doudna won the Nobel Prize in ChemistryFor the full story, visit: https://news.berk...

www.youtube.com

2

55

262

@pabbeel

Pieter Abbeel

1 year

Thank you @geoffreyhinton for diving deeper into the major potential risks you see with AI, and also reminding us of the tremendous potential for AI to improve our lives.

Tweet card media

S3 E9 Geoff Hinton, the "Godfather of AI", quits Google to warn of AI...

S3 E9 Geoff Hinton, the "Godfather of AI", quits Google to warn of AI risks (Host: Pieter Abbeel)What's in this episode:00:00:00 Geoffrey Hinton00:01:46 Spon...

www.youtube.com

8

50

265

@pabbeel

Pieter Abbeel

5 years

Video of Lecture 2 of CS294-158 Deep Unsupervised Learning is up We cover: - Autoregressive Models: MADE, Wavenet, PixelCNN(++), pixelsnail (self-attention) [ctd] - Lossless Compression - Flow Models: NICE, RealNVP, AF, neural AF, IAF, Glow, Flow++

Tweet card media

Week 2 CS294-158 Deep Unsupervised Learning (2/6/19)

UC Berkeley CS294-158 Deep Unsupervised Learning (Spring 2019)Instructors: Pieter Abbeel, Xi (Peter) Chen, Jonathan Ho, Aravind Srinivashttps://sites.google....

www.youtube.com

4

56

259

@pabbeel

Pieter Abbeel

3 years

One of our key values at @CovariantAI is to always be learning. As part of this I have much enjoyed explaining the core ideas behind recent AI Robotics progress to our customers and partners. Had some fun producing this with some new animations:

Tweet card media

AI Robotics for the Real World

At Covariant we are committed to research and development that will bring AI Robotics to the real world. As a part of this, we believe it's important to educ...

www.youtube.com

3

35

254

@pabbeel

Pieter Abbeel

5 years

Finally got to read this wonderful tutorial on transformers by @pbloemesquire !

@pbloemesquire

Peter Bloem (@[email protected])

5 years

New blogpost! Transformers from scratch. Modern transformers are super simple, so we can explain them in a really straightforward manner. Includes pytorch code.

Tweet media one

Tweet media two

Tweet media three

Tweet media four

17

453

2K

0

62

250

@pabbeel

Pieter Abbeel

5 years

My slides from yesterday's talk on "Some of our Explorations of Exploration in RL" -- surveying many directions of work in exploration

Tweet media one

Tweet media two

4

51

253

@pabbeel

Pieter Abbeel

3 months

Since AlexNet/ImageNet moment in October 2012, stock multiples: nvidia: ~250x amd: ~80x intel: ~2x

8

19

252

@pabbeel

Pieter Abbeel

3 years

Very excited to share our #ICML2021 tutorial materials on Unsupervised Learning for RL: w/ @AravSrinivas Part I covers Representation Learning for RL. Part II covers Unsupervised Pre-Training for RL.

Tweet card media

Unsupervised Reinforcement Learning

Pieter Abbeel, Aravind Srinivas UC Berkeley

sites.google.com

0

55

250

@pabbeel

Pieter Abbeel

6 years

NIPS Deep RL Workshop is happening again in 2018! Paper submission deadline is Friday Oct 12th. Exciting invited speakers line-up: @ylecun , Satinder Singh, Sham Kakade, @jeffclune , Doina Precup, Martha White, @jacobandreas !

Tweet card media

Deep RL Workshop NeurIPS 2018

About In recent years, the use of deep neural networks as function approximators has enabled researchers to extend reinforcement learning techniques to solve increasingly complex control tasks. The...

sites.google.com

0

65

246

@pabbeel

Pieter Abbeel

6 years

"Our results include using an entire NVIDIA DGX-1 to learn successful strategies in Atari games in single-digit minutes." (thanks @nvidia !) Also snuck in a 400K on seaquest (Fig. 4) :p Accelerated Methods for Deep Reinforcement Learning led by Adam Stooke

Tweet card media

Accelerated Methods for Deep Reinforcement Learning

Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-around time remains a key bottleneck in research and in practice. We investigate how to optimize existing...

2

75

239

@pabbeel

Pieter Abbeel

5 months

Biggest pro-tip I got in 2023 (h/t @RichardSocher ): Keeping two dumbbells right on my desk, for quick lifts in little dead moments between meetings, when listening to a seminar, etc. Went from when will I ever have time to lift again to lifting multiple times every day

8

13

237

@pabbeel

Pieter Abbeel

7 years

Great feature on high schooler Kevin Frans, 1st author on just released @openai HRL paper, amazing to work with!

0

65

237

@pabbeel

Pieter Abbeel

27 days

Great guest lecture yesterday by John Ingraham on Generative Models for Science

Tweet card media

L13a Generative Modeling for Science -- Guest Lecturer John Ingraham

CS294-158 Deep Unsupervised LearningUC Berkeley Spring 2024Instructors: Pieter Abbeel, Kevin Frans, Philipp Wu, Wilson Yancourse website: https://sites.googl...

www.youtube.com

2

45

234

@pabbeel

Pieter Abbeel

7 years

Vlad Minh at DeepRLBootcamp: Everything in Deep RL is still exciting. Nothing is solved. @VladMnih

Tweet media one

Tweet media two

4

80

228

@pabbeel

Pieter Abbeel

4 years

Couldn’t be more excited about what we are building! Yet, even more excited about @CovariantAI team, all brilliant and exceptional at working across team boundaries, engineering, research, business, we are all having fun and getting it done together!

Tweet media one

@CovariantAI

Covariant

4 years

After 2+ years in stealth, we’re excited to launch today! Thank you to our team, customers, partners and investors, we couldn’t have done it w/o your support and trust. Exciting milestone, even more exciting journey ahead!

17

120

689

6

23

227

@pabbeel

Pieter Abbeel

3 months

Current works are restricted to short sequences of texts and images, limiting their ability to model the world. Presenting Large World Model (LWM): capable of processing long text, images, videos of over 1M tokens (and *no* lost in the middle!) Project:

@haoliuhl

Hao Liu

3 months

We are excited to share Large World Model (LWM), a general-purpose 1M context multimodal autoregressive model. It is trained on a large dataset of diverse long videos and books using RingAttention, and can perform language, image, and video understanding and generation.

Tweet media one

Tweet media two

Tweet media three

25

263

1K

6

35

223

@pabbeel

Pieter Abbeel

6 years

Slides from my #ICRA2018 keynote on Deep Learning to Learn: photo credit @petitegeek

Tweet media one

4

54

221

@pabbeel

Pieter Abbeel

4 months

Love the content and how this is done! Great insights into how @berkeley_ai Prof. Mike Jordan thinks about the future of AI and also a look into his research style And thank you Barbara Rosario for creating!

Tweet card media

Talking about AI with the Italian Michael Jordan

Prof. Michael Jordan offers his provocative thoughts on the blending of AI and economics and takes us on a tour of Trieste, a beautiful and grand city in nor...

www.youtube.com

4

41

220

@pabbeel

Pieter Abbeel

6 years

Existing RL methods can be adapted to learn robust control policies capable of imitating a broad range of example motion clips, while also learning complex recoveries. paper: w/ @jasonpeng0 Sergey Levine @Mvandepanne

Tweet card media

DeepMimic: Example-Guided Deep Reinforcement Learning of...

A longstanding goal in character animation is to combine data-driven specification of behavior with a system that can execute a similar behavior in a physical simulation, thus enabling realistic...

1

79

217

@pabbeel

Pieter Abbeel

6 years

Beautiful op-ed and food for thought by Michael Jordan!

2

80

213

@pabbeel

Pieter Abbeel

3 years

On Ep20 of @therobotbrains , I sit down with the amazing @drfeifei , Co-Director of @StanfordHAI , Member of Nat'l Acad. of Medicine She shares ImageNet origin stories, her interest in physics leading to AI, her work in AI for Medicine, on the Nat'l AI Research Resource Task Force

Tweet media one

4

34

216

@pabbeel

Pieter Abbeel

6 years

#nips2017 Meta Learning Symposium videos are now available here: Thanks to Risto Miikkulainen, Quoc Le, Kenneth Stanley, and Chrisantha Fernando for organizing!

0

78

208

@pabbeel

Pieter Abbeel

4 years

My #ICRA2020 keynote video is now available: "Can Deep RL from Pixels be made as efficient as from State?" w/ @MishaLaskin @Aravind7694 @kimin_le2 @LerrelPinto AdamStooke

2

52

210

@pabbeel

Pieter Abbeel

2 years

Key open challenges @ylecun listed

Tweet media one

7

24

207

@pabbeel

Pieter Abbeel

3 years

Second episode of The Robot Brains podcast is live now! I was lucky enough to sit down with Princeton Professor @orussakovsky and dive into many of the possible issues with the data powering AI systems and what led her to start @ai4allorg !

4

36

207

@pabbeel

Pieter Abbeel

2 years

with real-world robotic experiments still more costly and time-consuming than simulated experiments, really exciting to see these major mujoco updates!

@GoogleDeepMind

Google DeepMind

@GoogleDeepMind

2 years

Introducing the #MuJoCo Menagerie, a collection of robot models curated by DeepMind: 1/

11

188

845

2

31

209

@pabbeel

Pieter Abbeel

6 years

Congratulations Dr Rocky Duan!!! Hard to believe how much you got done, and all in just over 2 years! "Meta Learning for Control" Thrilled to still be working together, putting AI/robotics into manufacturing and logistics at :)

Tweet media one

Tweet media two

Tweet media three

Tweet media four

4

30

207

@pabbeel

Pieter Abbeel

8 years

Deep Reinforcement Learning NIPS workshop so overcrowded that the security guard decided to keep out Rich Sutton!

Tweet media one

3

48

205

@pabbeel

Pieter Abbeel

6 years

Very excited to be giving a tutorial on Deep RL at @NASA next couple of days, and very curious about their use cases!

Tweet media one

2

12

206

@pabbeel

Pieter Abbeel

2 years

We were so fortunate to have @ylecun visit @UCBerkeley yesterday. Here is the talk recording:

Tweet card media

Yann LeCun: From Machine Learning to Autonomous Intelligence

EECS Colloquium Wednesday, September 27, 2022Banatao Auditorium, 310 Sutardja Dai Hall4-5pCaption available upon request

www.youtube.com

2

38

205

@pabbeel

Pieter Abbeel

6 years

We (led by @peterxichen ) introduce a new generative model architecture combining causal convolutions with self attention. New SOTA log-likelihood results on CIFAR-10 (2.85 bits per dim) and 32×32 ImageNet (3.80 bits per dim). and

Tweet card media

GitHub - neocxi/pixelsnail-public

Contribute to neocxi/pixelsnail-public development by creating an account on GitHub.

0

62

204