Exploring Open-Ended Algorithms: POET
About this episode
Three YouTubers; Tim Scarfe - Machine Learning Dojo (https://www.youtube.com/channel/UCXvHuBMbgJw67i5vrMBBobA), Connor Shorten - Henry AI Labs (https://www.youtube.com/channel/UCHB9VepY6kYvZjj0Bgxnpbw) and Yannic Kilcher (https://www.youtube.com/channel/UCZHmQk67mSJgfCCTn7xBfew). We made a new YouTube channel called Machine Learning Street Talk. Every week we will talk about the latest and greatest in AI. Subscribe now!
Special guests this week; Dr. Mathew Salvaris (https://www.linkedin.com/in/drmathewsalvaris/), Eric Craeymeersch (https://www.linkedin.com/in/ericcraeymeersch/), Dr. Keith Duggar (https://www.linkedin.com/in/dr-keith-duggar/), Dmitri Soshnikov (https://www.linkedin.com/in/shwars/)
We discuss the new concept of an open-ended, or "AI-Generating" algorithm. Open-endedness is a class of algorithms which generate problems and solutions to increasingly complex and diverse tasks. These algorithms create their own curriculum of learning. Complex tasks become tractable because they are now the final stepping stone in a lineage of progressions. In many respects, it's better to trust the machine to develop the learning curriculum, because the best curriculum might be counter-intuitive. These algorithms can generate a radiating tree of evolving challenges and solutions just like natural evolution. Evolution has produced an eternity of diversity and complexity and even produced human intelligence as a side-effect! Could AI-generating algorithms be the next big thing in machine learning?
Wang, Rui, et al. "Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions." arXiv preprint arXiv:2003.08536 (2020). https://arxiv.org/abs/2003.08536
Wang, Rui, et al. "Paired open-ended trailblazer (poet): Endlessly generating increasingly complex and diverse learning environments and their solutions." arXiv preprint arXiv:1901.01753 (2019). https://arxiv.org/abs/1901.01753
Watch Yannic’s video on POET: https://www.youtube.com/watch?v=8wkgDnNxiVs
and on the extended POET: https://youtu.be/gbG1X8Xq-T8
Watch Connor’s video https://www.youtube.com/watch?v=jxIkPxkN10U
UberAI labs video: https://www.youtube.com/watch?v=RX0sKDRq400
#reinforcementlearning #machinelearning #uber #deeplearning #rl #timscarfe #connorshorten #yannickilcher
Get every episode summarized
Each time Machine Learning Street Talk (MLST) publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from Machine Learning Street Talk (MLST)
AI 2040: Plan A report - Daniel Kokotajlo & Thomas Larsen
Machine Learning Street Talk (MLST)
Designing How AI Grows — Tom McGrath
Machine Learning Street Talk (MLST)
Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander...
Machine Learning Street Talk (MLST)
Every Exponential Ends — Silicon Valley Forgot — Adam Becker
Machine Learning Street Talk (MLST)