Jeff Clune @jeffclune profile

Jeff Clune

@jeffclune

Followers

23,584

Following

415

Media

306

Statuses

2,855

Professor, CS, U. British Columbia. CIFAR AI Chair, Vector Institute. Sr. Advisor, DeepMind | ML, AI, deep RL, deep learning, AI-Generating Algorithms (AI-GAs)

https://t.co/Gv6XP1Hozt

Paradise (Vancouver, BC)

Joined July 2010

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

Explore tweets Explore followers Explore following

Explore trending content on Musk Viewer

BTS BTS BTS • 796278 Tweets

#2024BTSFESTA • 220719 Tweets

#BANGBANGCON24 • 156783 Tweets

アクリル • 72351 Tweets

The Red Bullet • 71641 Tweets

Afghanistan • 64913 Tweets

Bangtan • 59199 Tweets

クロスプレイ • 57968 Tweets

#GFRunTheWorldConcert • 57940 Tweets

#RIIZINGDAY_in_BKK • 46185 Tweets

Hobi • 40632 Tweets

不知火舞 • 35145 Tweets

水分補給 • 31081 Tweets

テリーと舞 • 18144 Tweets

hoseok • 17879 Tweets

wings tour • 17694 Tweets

ブルーインパルス • 17647 Tweets

アスラン • 17345 Tweets

Broner • 16757 Tweets

バイソン • 16266 Tweets

オカシラ連合 • 15864 Tweets

クマローラー • 15226 Tweets

Rasta • 12873 Tweets

GIGIL SA SHOWTIME • 12575 Tweets

アトラスフェス • 11912 Tweets

ワイルズ • 11269 Tweets

コートアリシアン

テンカジョウ

ガルサブランカ

Flicky

ニコニコメンテ

虹7th

Om Shanti

福永ホームラン

グリフィン

タクティカルトライデッキ

RUN BTS

セカシン

津田ちゃん

Chris Christie

クマロラ

Baloch Missing Persons Day

WE ARE BULLETPROOF

響ちゃん

IKKOさん

MIC DROP

虚数巡狩

守りキーホルダー

ビッグラン

#BloomInManila

Last Seen Profiles

@redbites

@ActiveWCC

@zanybros

@Iinebackerblue

@RyanChristie2

@OcaLucho

@GregAllen315

@SaladKayi

@mahralho

@BGCoonLab

@J16158687078902

@ApostolosAndre9

@stillqueeraf

@maryonoreall

@JaneZiemer

@OUTandPROUD

@sotwecom

@uwuxxsuni

@Le0nzx

@melisugur

Pinned Tweet

Jeff Clune

@jeffclune

10 days

I am thrilled to introduce OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code. Led by @maxencefaldor and @jennyzhangzt , with @CULLYAntoine and myself. 🧵👇

10

36

188

Jeff Clune

@jeffclune

4 years

I am extremely excited to announce (1) I've joined OpenAI to lead a large-scale effort into AI-generating Algorithms research, & (2) I'll be an Associate CS Professor at U. British Columbia in 2021, where I will continue to lead the OpenAI project. Both are dreams come true! 1/2

79

110

2K

Jeff Clune

@jeffclune

1 year

Excited to announce I have joined DeepMind as a Senior Research Advisor! I will be working with many fantastic people there on AI-generating algorithms & open-ended learning, one of many areas where @DeepMind is a leader. My roles at UBC & the Vector Institute will stay the same.

56

70

2K

Jeff Clune

@jeffclune

2 years

Introducing Video PreTraining (VPT): it learns complex behaviors by watching (pretraining on) vast amounts of online videos. On Minecraft, it produces the first AI capable of crafting diamond tools, which takes humans over 20 minutes (24,000 actions) 🧵👇

23

318

2K

Jeff Clune

@jeffclune

6 years

My favorite example of when AI surprised us, the scientists wielding it. A corner case in our algo challenged AI to learn to walk without touching its feet to the ground. Many more in from @joelbot3000with @jb_mouret @CULLYAntoine Cully et al Nature 2015

10

397

1K

Jeff Clune

@jeffclune

3 years

Thrilled to share that "First return, then explore" appears today in Nature! Go-Explore solves all unsolved Atari games*, ending a long quest by the field that began in Nature. Led by @AdrienLE & @Joost_Huizinga w @joelbot3000 @kenneth0stanley & myself. 1/

19

190

794

Jeff Clune

@jeffclune

5 years

Introducing POET: it generates its own increasingly complex, diverse training environments & solves them. It automatically creates a learning curricula & training data, & potentially innovates endlessly! By @ruiwang2uiuc w/ @joelbot3000 & @kenneth0stanley

15

237

770

Jeff Clune

@jeffclune

1 year

Introducing Thought Cloning: AI agents learn to *think* & act like humans by imitating the thoughts & actions of humans thinking out loud while acting, enhancing performance, efficiency, generalization, AI Safety & Interpretability. Led by @shengranhu 1/5

14

145

604

Jeff Clune

@jeffclune

4 years

Today is my last day at Uber. It's been a dream to have our startup acquired by Uber &, with wonderful colleagues, create Uber AI Labs. I'm proud of our work, eg. Go-Explore, POET, AI-GAs, GTNs, ANML, Differentiable Plasticity, Backpropamine, Deep Neuroevolution, PPGNs, etc. 1/3

19

17

583

Jeff Clune

@jeffclune

6 years

Montezuma’s Revenge solved! 2 million points & level 159! Go-Explore is a new algorithm for hard-exploration problems. Shatters Pitfall records too 21,000 vs 0 Blog: Vid By @AdrienLE @Joost_Huizinga @joelbot3000 @kenneth0stanley & me

Montezuma’s Revenge Solved by Go-Explore (Sets Records on Pitfall too)

Solving the Atari games Montezuma’s Revenge and Pitfall has been a long-standing AI grand challenge. These games represent a broad class of challenging, real...

www.youtube.com

18

188

485

Jeff Clune

@jeffclune

4 years

Introducing Generative Teaching Networks, which generate entirely synthetic data that is up to 9x faster to train on than real data!, enabling state-of-the-art Neural Architecture Search Led by @felipesuch w @kenneth0stanley , @joelbot3000 , & @AdityaRawaI 1/

8

103

439

Jeff Clune

@jeffclune

1 month

Delighted to share that I've been promoted to Professor (aka “Full Professor”) A huge thanks to my wife, students, collaborators, colleagues, family, & friends for everything. It's been an exhilarating, wondrous, fascinating climb, and what a view! Now, which peak to climb next?

63

9

427

Jeff Clune

@jeffclune

6 years

Welcoming the era of deep neuroevolution. Simple GA trains DNNs on Atari (competes with DQN, A3C, ES). Random search also competitive!

Welcoming the Era of Deep Neuroevolution | Uber Blog

By leveraging neuroevolution to train deep neural networks, Uber AI Labs is developing solutions to solve reinforcement learning problems.

www.uber.com

10

147

401

Jeff Clune

@jeffclune

4 years

We're hiring software engineers, research engineers, & research scientists on the multi-agent team @OpenAI ! Interested in AI-generating algorithms, many interacting agents, open-ended algorithms, automatically generating training environments, deep RL etc?

16

69

381

Jeff Clune

@jeffclune

4 years

Reviewers in my experience almost always insist on SOTA for publication. This is the result. In doing so, we are asking to be lied to via p-hacking and brittle, non-reproducible results. We also choke off promising directions that are not immediately better, which is ridiculous!

utku

@utkuevci

4 years

Reviewing NeuRIPS papers one thing is clear: most of us think, our work needs to be better than others to get published and we sell(modify+highlight+hide) it to convince the reader, putting science second to it.

6

24

292

7

49

380

Jeff Clune

@jeffclune

6 years

We have open sourced the code behind the neuroevolution papers described in our blog post This includes the code for the deep genetic algorithm that is competitive for Deep RL. We hope this helps the community. Please let us know if you try them.

Welcoming the Era of Deep Neuroevolution | Uber Blog

By leveraging neuroevolution to train deep neural networks, Uber AI Labs is developing solutions to solve reinforcement learning problems.

www.uber.com

3

142

365

Jeff Clune

@jeffclune

3 years

I am recruiting PhD students at UBC. I especially encourage applications from those underrepresented in our field. Interested in AI-GAs, meta-learning, generating learning challenges, deep RL, open-endedness, QD, exploration, generalization, continual learning, etc? Please apply!

7

87

356

Jeff Clune

@jeffclune

8 years

Introducing Plug & Play Generative Networks. These are images synthetically generated by #DeepNeuralNetworks . More:

3

186

346

Jeff Clune

@jeffclune

7 years

We've open sourced the code for Plug & Play Generative Networks (PPGNs), which produced these images: Game on!

3

161

336

Jeff Clune

@jeffclune

4 years

Learning to Continuously Learn. ANML meta-learns to reduce catastrophic forgetting, and can learn at least 600 tasks (Omniglot classes) sequentially and performs well on most afterwards. arXiv NeurIPS talk Led by Shawn Beaulieu 1/2

6

86

328

Jeff Clune

@jeffclune

1 year

I agree. "I'm amazed that people confidently pronounce these things are not sentient, and when you ask them what they mean by sentient they say well they don't really know. So how can you be confident they're not sentient if you don't know what sentient means? "-Geoff Hinton 1/2

41

35

311

Jeff Clune

@jeffclune

1 year

No privacy concerns here. Nope. None at all.

AI Breakfast

@AiBreakfast

1 year

🤯 Full body tracking now possible using only WiFi signals A deep neural network maps the phase and amplitude of WiFi signals to UV coordinates within 24 human regions The model can estimate the dense pose of multiple subjects by utilizing WiFi signals as the only input 🧵

93

1K

5K

13

40

300

Jeff Clune

@jeffclune

5 years

AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence Historically, hand-designed pipelines are ultimately outperformed by entirely learned ones. Will that will be true of creating general AI itself? 1/6

16

104

268

Jeff Clune

@jeffclune

4 years

Introducing the Synthetic Petri Dish for architecture search: Creates tiny NN variants in a "dish" & optimizes synthetic data to make variants perform like their full NN counterparts. Then rapid NAS search in the dish. Generalizes better than NN models! 1/

2

51

258

Jeff Clune

@jeffclune

4 years

Neural Networks are Surprisingly Modular.

Pruned Neural Networks are Surprisingly Modular

The learned weights of a neural network are often considered devoid of scrutable internal structure. To discern structure in these weights, we introduce a measurable notion of modularity for...

arxiv.org

6

52

255

Jeff Clune

@jeffclune

4 years

Here is the final link to my talk at the ICLR BeTR-RL workshop on AI-GAs and Learning to Continually Learn (with ANML). Thanks to the workshop organizers and my collaborators! #ICLR2020 #iclr

6

61

250

Jeff Clune

@jeffclune

4 years

I think biological development is the most impressive technology in the known universe. Can you think of anything more impressive? A seed (or egg) uses nanotech to gather all the resources needed to self-assemble molecules into a jaguar, hawk, oak tree, whale or human. Amazing!

Andrej Karpathy

@karpathy

4 years

A human body is so wonderfully nested. Its ~40T cells descend from individual eukaryotic cells before multi-cellularity. And each has ~1000 mitochondria, which were free-living bacteria before endosymbiosis. And all of it is home to 1-3X as many bacteria in the nooks and crannies

35

105

1K

11

27

248

Jeff Clune

@jeffclune

4 years

Go-Explore now solves all unsolved Atari games*, handles stochastic training throughout via goal-conditioned polices, reuses skills to intelligently explore after returning, and solves hard-exploration simulated robotics tasks! New paper led by @AdrienLE & @Joost_Huizinga 1/6

10

64

234

Jeff Clune

@jeffclune

4 years

My picks are included. What are yours? Mine: LRL by @janexwang et al. (see also RL^2) and Reversible Learning by @DougalMaclaurin @ryan_p_adams @DavidDuvenaud . Both papers helped inspire AI-Generating Algorithms & its bet on meta-learning, GTNs, & ANML!

AI Paper Recommendations from Experts

We reached out to further members of the AI community for their recommendations of papers which everyone should be reading! All of the cited papers are free to access and cover a range of topics from...

blog.re-work.co

1

67

222

Jeff Clune

@jeffclune

1 year

Delighted to announce my lab @UBC_CS was awarded a substantial grant from Open Philanthropy for work on AI alignment, safety, & existential risk. I want to make the development of powerful AI & AGI go as well as possible for humanity, & will allocate more time to these key topics

16

21

220

Jeff Clune

@jeffclune

6 months

Most beautiful campus on Earth? What are other contenders?

UBC Computer Science

@UBC_CS

6 months

Wishing you and yours a safe, happy, and relaxing holiday season! 💗

2

4

68

31

11

219

Jeff Clune

@jeffclune

4 years

Introducing Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions.Adds domain-general metrics of environment novelty and progress in open-ended algorithms + a new environment search space 1/

5

57

215

Jeff Clune

@jeffclune

6 years

Generating multi-modal robot behavior (neural networks that perform many different tasks well) via the new Combinatorial Multi-Objective Evolutionary Algorithm (CMOEA). Very proud of this work. Led by Joost Huizinga @joosthuizinga Key idea: the more stepping stones the better!

5

64

211

Jeff Clune

@jeffclune

1 year

Excited to share OMNI: Open-endedness via Models of human Notions of Interestingness. Lead: @jennyzhangzt Open-ended learning requires a vast space of possible tasks, but search thus can get lost. Agents must focus only on *interesting* tasks, but how?🧵1/

7

49

210

Jeff Clune

@jeffclune

6 years

Very cool to see a replication of our paper "Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning"! Includes step-by-step instructions for AWS. Great work @TDataScience

Paper Repro: Deep Neuroevolution

“Deep Neuroevolution” showed that simple genetic algorithms can outperform advanced RL algorithms on Atari games. Let’s reproduce it!

towardsdatascience.com

1

77

204

Jeff Clune

@jeffclune

4 years

Here is a new talk entirely on ANML (a Neuromodulated Meta-Learning Algorithm) @reworkAI ANML meta-learns to reduce catastrophic forgetting, and can learn at least 600 tasks sequentially! paper: Learning to Continually Learn () #AI

8

65

201

Jeff Clune

@jeffclune

5 years

Yann LeCun @ylecun et al. publishing evolutionary algorithm tools. Welcoming the era of deep neuroevolution indeed! () Great to see the traditional ML community adopt these tools in the cases when they are useful.

Welcoming the Era of Deep Neuroevolution | Uber Blog

By leveraging neuroevolution to train deep neural networks, Uber AI Labs is developing solutions to solve reinforcement learning problems.

www.uber.com

hardmaru

@hardmaru

5 years

This library from @ylecun ’s lab implemented benchmarked versions of evolutionary computation algorithms such as: Differential Evolution, Fast Genetic Algorithm, CMA-ES, Particle Swarm Optimization. 🦎🐞🐜

2

61

261

0

61

201

Jeff Clune

@jeffclune

3 years

AI-GAs++ It's learned optimizers all the way down!🐢🐢🐢 Training Learned Optimizers with Randomly Initialized Learned Optimizers

Training Learned Optimizers with Randomly Initialized Learned Optimizers

Learned optimizers are increasingly effective, with performance exceeding that of hand designed optimizers such as Adam~\citep{kingma2014adam} on specific tasks \citep{metz2019understanding}....

arxiv.org

5

34

193

Jeff Clune

@jeffclune

1 year

My AI-Generating Algorithms paper described "Darwin-complete" environment search spaces: those that can represent any environment. I suggested one then: neural network world models. Another is code (e.g. LM-generated code for environments/simulators/games)

2

36

188

Jeff Clune

@jeffclune

3 months

One amazing thing Genie enables: anyone, including children, can draw a world and then *step into it* and explore it!! How cool is that!?! We tried this with drawings my children made, to their delight. My child drew this, and now can fly the eagles around. Magic!🧞✨

Jeff Clune

@jeffclune

3 months

Excited to share a project I've been working on at DeepMind. It's very cool & futuristic, with great potential for generating interactive worlds & agent training environments. Congrats to the team for the amazing work, especially leads @ashrewards @jparkerholder & @_rockt 🧵🚀👇🏽

8

17

165

5

31

187

Jeff Clune

@jeffclune

5 years

Our paper was accepted at ICLR. Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity. Very exciting work led by @ThomasMiconi , a pioneer in this area. With Aditya Rawal, @kenneth0stanley , and myself @iclr2019

Backpropamine: training self-modifying neural networks with...

Neural networks can be trained to modify their own connectivity, improving their online learning performance on challenging tasks.

openreview.net

0

39

184

Jeff Clune

@jeffclune

5 years

In the ICLR Debate I introduced an alternate path to general AI: AI-generating algorithms (AI-GAs), and the Three Pillars required to make AI-GAs. Full debate (on how much we should learn vs. build in): w Tenenbaum, Precup, Kaelbling, @suchisaria Thoughts?

14

39

181

Jeff Clune

@jeffclune

5 years

I am extremely honored to receive the Presidential Early Career Award for Scientists and Engineers (PECASE) from the White House: Thanks to all of my wonderful collaborators and mentors throughout my career, without whom this would not be possible.

14

7

183

Jeff Clune

@jeffclune

4 years

Join us! Our team at OpenAI is now hiring research scientists and engineers. Interested in AI-generating algorithms, multiple interacting agents, open-ended algorithms, automatically generating training environments, deep RL, and more? Please apply!

9

35

183

Jeff Clune

@jeffclune

8 months

I, with 3 Turing Award winners (including @geoffreyhinton , Bengio, Yao), Nobel laureate @kahneman_daniel , & other leaders in AI and AI governance, release a paper today recommending specific government & company actions on AI development to minimize risk

AI firms must be held responsible for harm they cause, ‘godfathers’ of technology say

Authors and academics also warn development of advanced systems ‘utterly reckless’ without safety checks

www.theguardian.com

6

42

182

Jeff Clune

@jeffclune

2 years

Agreed. I remember when I told journalists in 2016 AI would be able to generate any image you (or bad actors) want from a text description and they thought I was nuts. I also predicted videos and entire virtual worlds would come later, which they will! Strap in, society.

hardmaru

@hardmaru

2 years

AI Images: Last Week Tonight with John Oliver Text-to-Image has really gone mainstream! Source:

7

80

353

5

20

180

Jeff Clune

@jeffclune

4 years

I greatly enjoyed giving a guest lecture in @chelseabfinn 's meta-learning class at Stanford. Thanks to Chelsea for the invitation & for making all of the lectures available for everyone! Mine is a deep dive into AI-GAs, GTNs, differentiable plasticity/backpropamine, ANML, & POET.

Chelsea Finn

@chelseabfinn

4 years

Want to learn about meta-learning? Lecture videos for CS330 are now online! Topics incl. MTL, few-shot learning, Bayesian meta-learning, lifelong learning, meta-RL & more: + 3 guest lectures from Kate Rakelly, @svlevine , @jeffclune

33

686

3K

1

24

173

Jeff Clune

@jeffclune

6 years

Introducing a new, totally different type of meta-learning: gradient-based Hebbian learning (stores info in weights, not activations). Congrats to @ThomasMiconi ! With @kenneth0stanley Differentiable Plasticity: A New Method for Learning to Learn @ubereng

2

57

169

Jeff Clune

@jeffclune

5 years

Here are the slides from my talk on Go-Explore at the #NeurIPS2018 Deep Reinforcement Learning workshop.

5

44

174

Jeff Clune

@jeffclune

6 years

Today we are open sourcing a new tool called VINE that visualizes deep neuroevolution populations learning over time. Project led by Rui Wang and Ken Stanley. We hope the community benefits from it! via @ubereng

2

78

173

Jeff Clune

@jeffclune

11 months

Introducing: First-Explore, then Exploit: Meta-Learning Intelligent Exploration. Led by @BenNorman451 Humans are masters at exploring. Unlike RL, we do not explore by trying to maximize reward (with noise), but instead explore to gain information! 1/8

3

24

172

Jeff Clune

@jeffclune

2 years

Nice new work by DeepMind covered in Nature, with comments by yours truly. Congrats to the authors.

DeepMind AI learns simple physics like a baby

Nature - Neural network could be a step towards programs for studying how human infants learn.

www.nature.com

2

26

171

Jeff Clune

@jeffclune

5 years

Slides now available for our ICML Tutorial on Population-Based Methods for Training Deep Neural Networks: Novelty Search, Quality Diversity, Open-Ended Search Algorithms, & Indirect Encoding. w @kenneth0stanley & @joelbot3000 #icml2019 Video soon.

3

42

172

Jeff Clune

@jeffclune

3 months

Excited to share a project I have been working on at DeepMind. Congrats to the entire, wonderful SIMA team! I look forward to hearing what the community thinks of this advance.

Google DeepMind

@GoogleDeepMind

3 months

Introducing SIMA: the first generalist AI agent to follow natural-language instructions in a broad range of 3D virtual environments and video games. 🕹️ It can complete tasks similar to a human, and outperforms an agent trained in just one setting. 🧵

188

873

4K

6

17

172

Jeff Clune

@jeffclune

6 years

Deep Curiosity Search introduces a new type of intrinsic motivation for deep RL: intralife exploration. Just rewarding agents to 'go somewhere new' can dramatically increase performance, tying state of the art on Montezuma’s Revenge Congrats Chris Stanton!

0

39

163

Jeff Clune

@jeffclune

2 years

VPT was accepted at NeurIPS! Congrats to the team for all the hard work, and a huge thanks to the @NeurIPSConf reviewers and organizers! #NeurIPS2022

Jeff Clune

@jeffclune

2 years

Introducing Video PreTraining (VPT): it learns complex behaviors by watching (pretraining on) vast amounts of online videos. On Minecraft, it produces the first AI capable of crafting diamond tools, which takes humans over 20 minutes (24,000 actions) 🧵👇

23

318

2K

6

15

168

Jeff Clune

@jeffclune

4 years

If Trump wins I am moving to Canada. I'm serious.

12

3

166

Jeff Clune

@jeffclune

3 months

Excited to share a project I've been working on at DeepMind. It's very cool & futuristic, with great potential for generating interactive worlds & agent training environments. Congrats to the team for the amazing work, especially leads @ashrewards @jparkerholder & @_rockt 🧵🚀👇🏽

Tim Rocktäschel

@_rockt

3 months

I am really excited to reveal what @GoogleDeepMind 's Open Endedness Team has been up to 🚀. We introduce Genie 🧞, a foundation world model trained exclusively from Internet videos that can generate an endless variety of action-controllable 2D worlds given image prompts.

144

575

2K

8

17

165

Jeff Clune

@jeffclune

4 years

"API for accessing new AI models developed by OpenAI. Unlike most AI systems which are designed for one use-case, the API today provides a general-purpose “text in, text out” interface, allowing users to try it on virtually any English language task."

4

28

163

Jeff Clune

@jeffclune

6 years

Update: Go-Explore remains state of the art on Montezuma’s & Pitfall when *tested* with sticky actions. Should we *require* stochastic training? Depends on the research objectives. Please read newly added section A healthy debate created by Go-Explore.

Montezuma��s Revenge Solved by Go-Explore, a New Algorithm for Hard-exploration Problems (Sets...

Uber AI Labs introduces Go-Explore, a new reinforcement learning algorithm for solving a variety of challenging problems, especially in robotics.

www.uber.com

6

41

164

Jeff Clune

@jeffclune

1 year

I often have ideas for startups, research papers, short stories, etc. I am going to start posting them here to share them, see what people think, and in the hopes of maybe inspiring someone to something related (or even implement the idea). I'll tag things with #someBodyDoThis

10

4

161

Jeff Clune

@jeffclune

4 years

Introducing Fiber, a new open source platform for distributed machine learning, especially population-based methods like Enhanced POET. Program locally with a standard multiprocessing API then deploy to thousands of workers on any cluster. Led by @_calio

4

51

159

Jeff Clune

@jeffclune

6 years

Momentum continues to build in Deep Neuroevolution. Another five-paper blog post, this time by Sentient. Congrats to Risto and all on the team! Evolution is the New Deep Learning

0

66

156

Jeff Clune

@jeffclune

5 years

Creating a Zoo of Atari-Playing Agents to Catalyze the Understanding of Deep Reinforcement Learning. Great work led by Joel Lehman @joelbot3000 , w/ many excellent collaborators from Uber AI Labs, OpenAI, & Google Brain. Blog: Code:

2

43

156

Jeff Clune

@jeffclune

9 months

I am delighted to report that Thought Cloning was not only accepted to NeurIPS @NeurIPSConf , but awarded a spotlight. Thanks to the AC, reviewers, and community. A huge congrats to @shengranhu ! #NeurIPS #neurips2023

Jeff Clune

@jeffclune

1 year

Introducing Thought Cloning: AI agents learn to *think* & act like humans by imitating the thoughts & actions of humans thinking out loud while acting, enhancing performance, efficiency, generalization, AI Safety & Interpretability. Led by @shengranhu 1/5

14

145

604

5

22

158

Jeff Clune

@jeffclune

6 years

Our paper was accepted @NipsConference ! Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents.Congrats to leads @vashmadhavan , Edoardo Conti, & the whole team @felipesuch @joelbot3000 @kenneth0stanley @UberAILabs

7

33

156

Jeff Clune

@jeffclune

2 years

I often have (what I think are) great ideas for startups (especially AI startups). Has someone created a way to suggest ideas to would-be entrepreneurs and then get a small bit of equity if they work on your idea? If not, is that itself a good idea (a site that does that)?

66

10

155

Jeff Clune

@jeffclune

1 year

How can I get rid of all the AI clickbait in my feed? It's mostly from blue checkmark folks. Is there a way to ban/ignore/filter anyone who has one? Are the rest of you inundated with annoying click-baity AI Tweets?

26

1

153

Jeff Clune

@jeffclune

6 years

Just realized our Deep Neuroevolution paper is on the front page of Hacker News! That's fun. Also the most talked about ML paper on Twitter this week according to @karpathy 's arXiv-sanity. Thanks all for your interest in our work!

2

27

147

Jeff Clune

@jeffclune

4 years

Here's the video of my ICML Continual Learning Workshop talk: "Learning to Continually Learn" introduces AI-GAs as a path to AGI and focuses on ANML as an example of that research paradigm that works well to minimize catastrophic forgetting #ICML2020

Jeff Clune · Learning to Continually Learn

A dominant trend in machine learning is that hand-designed pipelines are replaced by higher-performing learned pipelines once sufficient compute and data are available. I argue that trend will...

slideslive.com

3

45

144

Jeff Clune

@jeffclune

5 years

Don't aim for success if you want it; just do what you love and believe in, and it will come naturally. - David Frost (via the excellent book Why Greatness Cannot be Planned by @kenneth0stanley and @joelbot3000 ).

3

27

147

Jeff Clune

@jeffclune

4 years

I will be hiring at both institutions, so please watch this space for details on those opportunities if interested. A huge thanks to everyone at both OpenAI and UBC for these wonderful opportunities! I could not be more excited about both! 2/2

9

7

146

Jeff Clune

@jeffclune

6 years

Accelerating Deep Neuroevolution: Train Atari in Hours on a Single Personal Computer! What took ~1 hour on 720 CPUs now takes only ~4 hours on a *single* modern desktop. Code is open source. Awesome work by @felipesuch with @kenneth0stanley via @ubereng

0

55

144

Jeff Clune

@jeffclune

4 years

Thank you very much.

Reinforcement Learning Turkiye

@Turkiye_RL

4 years

In honor of @UberAILabs we wanted to share this quote from Jeff Clune ( @jeffclune ). We hope all researchers & developers can find a good place to work & continue to research in this pandemic . Your unique contributions to our field will always be remembered. #uberlabs

0

21

87

2

9

140

Jeff Clune

@jeffclune

4 years

We are beginning to see how powerful AI can catalyze science. In a future coming to you soon: ask the computer to conduct an experiment, interactively probe the results, and then ask for the next experiment, iterating quickly without writing a single line of code or pipetting!

ken

@aquariusacquah

4 years

GPT-3 Does The Work™️ on generating SVG charts, with a quick web app I built with @billyjeanbillyj . With a short sentence describing what you want to plot, its able to generate charts with titles, labels and legends from about a dozen primed examples. cc @gdb

20

175

739

6

36

139

Jeff Clune

@jeffclune

6 months

Here is a YouTube link to my #NeurIPS2023 invited talk "Open-ended and AI-generating Algorithms in the Era of Foundation Models." Includes exciting new OMNI results in an infinite task space. Lmkwyt! @NeurIPSConf @aloeworkshop @gcrl_workshop @jsuarez5341

Open-Endedness and AI GAs in the Era of Foundation Models

My talk at NeurIPS 2023 (given in the ALOE, Goal-Conditioned, and Neural MMO workshops). Foundation models create exciting new opportunities in our longstand...

www.youtube.com

2

36

142

Jeff Clune

@jeffclune

4 years

Fiber, an open source platform for distributed machine learning, esp population-based methods like Enhanced POET. Program locally with a standard multiprocessing API then deploy to thousands of workers on any cluster. @_calio @ruiwang2uiuc @kenneth0stanley

Fiber: Distributed Computing for AI Made Simple | Uber Blog

Fiber is a Python-based distributed computing library for modern computer clusters. Instead of programming only a single desktop or laptop, users can leverage this system to program the whole...

www.uber.com

1

48

132

Jeff Clune

@jeffclune

5 years

Nice new article on novelty search, QD, open-ended algos, and AI-generating algorithms, including connections to Go-Explore, AlphaStar, IT&E, & more. Thanks @SilverJacket for writing it and to @RaiaHadsell , @maxjaderberg , & @togelius for nice comments.

2

50

137

Jeff Clune

@jeffclune

6 years

Another great example of AI outsmarting us. Here scientists took a robot that could solve tasks by picking up a box and then disabled its gripper to see if it could adapt to push the box around. It instead figured out how to pick the box up anyway!

2

49

128

Jeff Clune

@jeffclune

3 years

Great article about AI-generating Algorithms ("getting AI to make itself"), including POET, GTNs, & ANML Also includes work & quotes from @ruiwang2uiuc (POET), Esteban Real (AutoML), & @janexwang (LRL), plus great work by @OpenAI Thanks for the fun interview & article @strwbilly !

MIT Technology Review

@techreview

3 years

Artificial intelligence might not need us to become smarter than we are. This thread is about how AI is learning how to create itself.

18

187

412

2

36

129

Jeff Clune

@jeffclune

6 years

Introducing a new algorithm that automatically, intelligently adjusts exploration vs. exploitation for #DeepRL . NSRA-ES exploits until stuck, then increasingly explores. It's newly added to 'Improving Exploration in ES' Great work on it Vashisht Madhavan!

Improving Exploration in Evolution Strategies for Deep...

Evolution strategies (ES) are a family of black-box optimization algorithms able to train deep neural networks roughly as well as Q-learning and policy gradient methods on challenging deep...

arxiv.org

1

25

129

Jeff Clune

@jeffclune

5 years

Nice article in Nature about how deep neural networks are easily fooled, covering our work over the years (w @anh_ng8 & @jasonyo ) and great work by many others (eg @ChrSzegedy , @goodfellow_ian , @dawnsongtweets ). Plus an interesting discussion on future AI.

1

41

130

Jeff Clune

@jeffclune

4 years

What is starting to happen to me during quarantine because of no haircuts.

Sami Abdul Aziz

@FarmerAziz

4 years

This sheep escaped a farm and spent 6 years in the mountains, during which time he grew 60 pounds of wool. Wolves tried to eat him, but their teeth could not penetrate the floof. You don't have to turn hard to survive the wolves, just be really, really soft and fluffy.

1K

44K

152K

7

126

Jeff Clune

@jeffclune

4 years

Generative Teaching Networks (GTNs) are on the homepage of Hacker News right now: I wonder why now? Blog post (from December):

6

18

125

Jeff Clune

@jeffclune

5 years

We are deeply honored to receive the Outstanding Paper of the Decade award from ISAL @alifeofficial for The Evolutionary Origins of Modularity (Proceedings Royal Society 2013). The work was co-led by @jb_mouret & with @hodlipson . Thanks Alife community!

2

15

125

Jeff Clune

@jeffclune

3 years

Very interesting new work on open-endedness and AI-Generating Algorithms from @maxjaderberg et al. @DeepMind , with special emphasis on Pillar 3 (automatically generating environments, like in POET). Congrats. I look forward to reading it in detail!

Max Jaderberg

@maxjaderberg

3 years

Very excited to release our new work: Open-Ended Learning Leads to Generally Capable Agents. tldr; algorithm that dynamically shapes task distributions to train agents on huge task space, resulting in surprisingly general behaviour Thread: (1/n)

10

216

875

2

15

125

Jeff Clune

@jeffclune

4 years

Open source code now available for ANML From Learning to Continually Learn (Beaulieu et al. ECAI 2020). ANML meta-learns how to learn without catastrophic forgetting, including up to 600 sequential tasks. Talk:

2

31

120

Jeff Clune

@jeffclune

5 years

Excited to give a talk at Stanford today to @chelseabfinn 's meta-learning and multi-task learning class (& open to all at Stanford). Thanks Chelsea for the invitation."How Meta-Learning Could Help Us Accomplish Our Grandest AI Ambitions, and Early, Exotic Steps in that Direction"

6

10

120

Jeff Clune

@jeffclune

6 years

Being an AI researcher as adult means reliving the video game part of my childhood in order. First Atari, then Super Mario, now streetfighter. Looking forward to Goldeneye next!

hardmaru

@hardmaru

6 years

The MAME RL Algorithm Training Toolkit: A Python library that can provide a Gym-like API around almost any old arcade game. They show how to set up new ROMS, and provide RL example for “Street Fighter III Third Strike: Fight for the Future (Japan version)”

7

209

617

7

20

119

Jeff Clune

@jeffclune

2 years

A friend of mine has cancer. I generated AI images of her as a superhero fighting cancer and she loved them. She asked if I could produce a 3D-printed version. Anyone know a talented 3D-blender-type artist that also knows how to 3D print their creations that I could hire?

13

14

119

Jeff Clune

@jeffclune

4 years

Source code is now available for Generative Teaching Networks Code Courtesy of @felipesuch 's amazing research & engineering. We hope this helps the community. Let us know if you use it! w/ @kenneth0stanley @joelbot3000 @AdityaRawaI

GitHub - uber-research/GTN

Contribute to uber-research/GTN development by creating an account on GitHub.

github.com

1

30

118

Jeff Clune

@jeffclune

4 years

Secretly our Enhanced POET project was an attempt to move closer to making this picture from @hardmaru 's ES blog post a reality. We use the same algorithm, and now have the cliff jumping! Next up: automating the generation of environments with parachutes!

2

26

118

Jeff Clune

@jeffclune

3 years

Watch this if you want to understand how the world will change. :-)

The Most Impressive AI Demo I Have Ever Seen - Marginal REVOLUTION

This is jaw-dropping. It starts slow but watch the whole thing. I don’t think I would have been more amazed had I witnessed the first flight of the Wright Brothers.

marginalrevolution.com

2

29

118

Jeff Clune

@jeffclune

1 year

My MIT talk is online. Thanks to Josh Tenenbaum for the nice introduction. "Improving Deep RL via Quality Diversity, Open-Ended, and AI-Generating Algorithms" (also covers VPT and how that fits into the AI-GA paradigm). Thanks @cedcolas for organizing!

Improving Deep Reinforcement Learning via Quality Diversity, Open-E...

Jeff Clune, Associate Professor, Computer Science, University of British Columbia; Canada CIFAR AI Chair and Faculty Member, Vector Institute; Senior Researc...

www.youtube.com

1

30

115

Jeff Clune

@jeffclune

1 year

Seeking a postdoc to join my lab at UBC! Interested in combining deep RL & large language models to advance open-endedness? Candidates should have pubs in one of: RL, large models, open-endedness, or related areas. 1-2+-year positions in paradise! Apply:

4

39

114

Jeff Clune

@jeffclune

3 years

Dear people who make utilities (e.g. websites, apps) that are free and helpful: thank you.

2

4

114

Jeff Clune

@jeffclune

5 years

Cool to see our evolved virtual creatures highlighted in Nature Machine Intelligence! Thanks to @Kriegmerica for the kind words in the article. Work with Nick Cheney, Rob MacCurdy, and Hod Lipson.

Josh Bongard

@DoctorJosh

5 years

Tired of training #NeuralNetworks ? Try optimizing virtual creatures instead. @nature Machine Intelligence article by Sam Kriegman ( @Kriegmerica ).

8

40

153

0

20

113

Jeff Clune

@jeffclune

2 years

I am delighted to announce that I have been appointed as Canada CIFAR AI Chair. Thanks to everyone at CIFAR and the Vector Institute. Congrats to the other appointees, including @VeredShwartz

UBC Computer Science

@UBC_CS

2 years

Happy to announce the appointments of two new Canada CIFAR AI Chairs from UBC Computer Science: Dr. Jeff Clune and Dr. Vered Shwartz Read about their research: @jeffclune @VeredShwartz @CIFAR_News @VectorInst #AI #NLP #UBC #CIFAR

4

11

35

14

5

113

Jeff Clune

@jeffclune

5 years

Slides available for my talk: "Endlessly Generating Increasingly Complex and Diverse Learning Environments and their Solutions through the Paired Open-Ended Trailblazer (POET)" Led by @ruiwang2uiuc with @joelbot3000 & @kenneth0stanley Video soon @reworkAI

1

23

111

Jeff Clune

@jeffclune

3 years

I wish arXiv put affiliations on the html page for a paper. Often that's the only reason I download the PDF, as I am curious where the work came from. I wonder how much bandwidth they'd save by doing that.

9

4

112