CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Machine Learning Street Talk (MLST)2 Touko 2020

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

According to Yann Le Cun, the next big thing in machine learning is unsupervised learning. Self-supervision has changed the entire game in the last few years in deep learning, first transforming the language world with word2vec and BERT -- but now it's turning computer vision upside down.


This week Yannic, Connor and I spoke with one of the authors, Aravind Srinivas who recently co-led the hot-off-the-press CURL: Contrastive Unsupervised Representations for Reinforcement Learning alongside Michael (Misha) Laskin. CURL has had an incredible reception in the ML community in the last month or so. Remember the Deep Mind paper which solved the Atari games using the raw pixels? Aravind's approach uses contrastive unsupervised learning to featurise the pixels before applying RL. CURL is the first image-based algorithm to nearly match the sample-efficiency and performance of methods that use state-based features! This is a huge step forwards in being able to apply RL in the real world.


We explore RL and self-supervision for computer vision in detail and find out about how Aravind got into machine learning.


Original YouTube Video: https://youtu.be/1MprzvYNpY8


Paper:

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

Aravind Srinivas, Michael Laskin, Pieter Abbeel

https://arxiv.org/pdf/2004.04136.pdf


Yannic's analysis video: https://www.youtube.com/watch?v=hg2Q_O5b9w4


#machinelearning #reinforcementlearning #curl #timscarfe #yannickilcher #connorshorten


Music credit; https://soundcloud.com/errxrmusic/in-my-mind

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(260)

Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov

Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov

Tim Scarfe speaks with Ilia Shumailov and Alexander Panfilov about their paper, Stealing Reasoning Traces from Proprietary LLM APIs.The core bug sounds deceptively simple: providers return encrypted r...

22 Elo 49min

Every Exponential Ends — Silicon Valley Forgot — Adam Becker

Every Exponential Ends — Silicon Valley Forgot — Adam Becker

Astrophysicist Adam Becker, author of "What Is Real?", joins Tim Scarfe to take apart the futures Silicon Valley keeps selling: the 2045 singularity, mind uploading, Mars colonies, and the AI apocalyp...

20 Elo 1h 18min

AI Is Learning at the Wrong Level of Abstraction — Matthieu Wyart

AI Is Learning at the Wrong Level of Abstraction — Matthieu Wyart

This episode is sponsored by Notion. Learn more about Notion's Developer Platform today at https://notion.com/mlstWhy can deep networks discover abstractions that shallow models miss? Statistical phys...

10 Elo 1h 18min

How Researchers Test AI for Hidden Goals — Apollo Research

How Researchers Test AI for Hidden Goals — Apollo Research

Can an AI do the right thing for the wrong reason? Tim Scarfe speaks with Apollo Research’s Alexander Meinke, Axel Højmark and Jérémy Scheurer about Measuring Reward-Seeking via Contrastive Belief Upd...

31 Heinä 1h 18min

Why a Nation Can't Outsource Its Frontier AI - Alistair Pullen (Cosine AI)

Why a Nation Can't Outsource Its Frontier AI - Alistair Pullen (Cosine AI)

This episode is sponsored by Notion. Learn more about Notion's Developer Platform today at https://notion.com/mlstBritain's most capable coding model can't be exported, and that ban is the whole reaso...

13 Heinä 55min

The Benchmark With No Instructions — ARC-AGI-3 (winning team!)

The Benchmark With No Instructions — ARC-AGI-3 (winning team!)

Tim Scarfe travels to Zurich to sit down with the Tufa Labs ARC-AGI-3 team — founder Benjamin Crouzier, with Jeroen Cottaar, Dries Smit, Stefano Viel and Michal Tesnar — to work out what their leaderb...

1 Heinä 1h 24min

The Thermodynamic AI Computing Chip - Thomas Ahle

The Thermodynamic AI Computing Chip - Thomas Ahle

Thomas Ahle wants Normal Computing to be the Lovable for chip design: type your intent, and a swarm of agents carries it from design through optimisation, formalisation and verification to tape-out. T...

28 Kesä 1h 2min

He won a Nobel here for AlphaFold. Then he left. - John Jumper

He won a Nobel here for AlphaFold. Then he left. - John Jumper

This episode is sponsored by Notion. Learn more about Notion's Developer Platform today at https://notion.com/mlstProtein folding stalled biology for fifty years. A sequence of amino acids dictates a ...

22 Kesä 53min