Jeff Clune (@jeffclune) | Robocrunch.Net

Jeff Clune @jeffclune

Associate Professor, CS, U. British Columbia. Research Team Leader, OpenAI. ML, AI, deep RL, deep learning, AI-Generating Algorithms (AIGAs) More: https://t.co/R4A5bg2MVu

Tweets by Jeff Clune

Cool to see startups come out of work done at Uber AI labs! Congrats and good luck Piero!!

Shared by Jeff Clune at 5/13/2022

Excited to speak at the ICLR @iclr_conf workshop on AI for Earth and Space Science today, sharing our work using deep learning to aid biologists study & conserve natural ecosystems (our PNAS paper to the present). I also love the pic they chose for me! https://t.co/rMhegBlRM4

Shared by Jeff Clune at 4/29/2022

Pleased to share a new review article on bio-inspired continual learning in Nature Machine Intelligence: "Biological underpinnings for lifelong learning machines" Thanks to the lead organizers for all the hard work, to the many excellent co-authors, and to Hava Siegelmann for L2M

Shared by Jeff Clune at 3/23/2022

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!

Shared by Jeff Clune at 7/27/2021

My @Mila_Quebec Tea Talk recording is now up in case you are interested. "AI-Generating Algorithms, an Alternate Paradigm for Producing General AI, and an Example in this Direction: Learning to Continually Learn" https://t.co/DXpVD4R6h6

Shared by Jeff Clune at 6/15/2021

Love this idea. From the paper "Decision Transformer can serve as a powerful “memorization engine” and in conjunction with powerful exploration algorithms like Go-Explore [28], has the potential to simultaneously model and generative a diverse set of behaviors."

Shared by Jeff Clune at 6/7/2021

I like this lay description of AI-GAs and the Three Pillars:"The long-term vision is to take all these techniques—and others not yet invented—and hand them over to an AI trainer that controls how artificial brains are wired, how they are trained, and what they are trained on."

Shared by Jeff Clune at 5/27/2021

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!

Shared by Jeff Clune at 5/27/2021