user avatar
Lisa Lee
@rl_agent
Gemini pre-training & post-training
leelisa.com
Joined February 2016
0
Following
5,794
Followers
Posts
  • user avatar
    Lisa Lee
    @rl_agent
    Oct 11, 2021
    Five years ago, I left Google to pursue a PhD in Machine Learning. Tomorrow, I'm very excited to join Google Brain as a Research Scientist! Looking forward to meeting everyone :) My PhD thesis can be viewed at: leelisa.com/pdf/phd_thesis… Thesis defense: youtu.be/P4LH020ON3A
  • user avatar
    Lisa Lee
    @rl_agent
    Jun 11, 2021
    Update: I will be a Research Scientist at Google Brain starting this fall! Super grateful to all of the fantastic researchers I met through the interview process. Thanks for valuable career advice & research chats – I'll take these lessons with me in the next stage of my career!
  • user avatar
    Lisa Lee
    @rl_agent
    Dec 6, 2023
    Gemini is the most fun project I've worked on in my career. I feel so lucky to work with incredible teammates in Gemini. We all worked really hard for this public release. Looking forward to more learnings in 2024. Chat with Bard (running Gemini Pro): bard.google.com/chat
    66K
  • user avatar
    Lisa Lee
    @rl_agent
    Jun 19, 2018
    Just released our #ICML2018 paper "Gated Path Planning Networks" as well as a @PyTorch implementation for replicating our experiments: arxiv.org/abs/1806.06408 github.com/lileee/gated-p… - with Emilio Parisotto, @dchaplot, Eric Xing, @rsalakhu See you @icmlconf in Stockholm!
  • user avatar
    Lisa Lee
    @rl_agent
    May 1, 2019
    I wrote a Colab tutorial on MaxEnt RL: colab.research.google.com/drive/1VkoRfg_… It implements the graphical model from @svlevine's "RL as Inference" tutorial for a simple chain environment. Play around with the reward function to learn different policies using the forward-backward algorithm!
    Colab logo
    colab.research.google.com
    RL as Probabilistic Inference
    Colaboratory notebook
  • user avatar
    Lisa Lee
    @rl_agent
    May 29, 2023
    My dog Eevee 🐶 is featured in our recent research paper from Google @DeepMind: Barkour: Benchmarking animal-level agility with quadruped robots Inspired by dog agility competitions, we introduce a diverse and challenging obstacle course for robotic locomotion. (1/n)
    00:00
    32K
  • user avatar
    Lisa Lee
    @rl_agent
    May 5, 2018
    I was a TA for @rsalakhu's 10-703 Deep Reinforcement Learning, with 500+ enrolled students. It was a little scary to hold office hours at first, but it got easier as I got to know more students. I was so touched to read these words from students. Thank you!
  • user avatar
    Lisa Lee
    @rl_agent
    May 5, 2019
    Excited to give two Contributed Talks @ #iclr2019 on Monday w/ Ben Eysenbach on our new work: Exploration & Meta-RL via State Marginal Matching leelisa.com/pdf/state_marg… w/ Ben, Emilio @rsalakhu @svlevine 12:15 @ TARL tarl2019.github.io/#schedule 15:50 @ SPiRL spirl.info/2019/program
    GIF
  • user avatar
    Lisa Lee
    @rl_agent
    Jul 10, 2023
    What makes it hard for robots to generalize to new environments? In our study, we broke down the notion of an “environment” into smaller, more manageable factors of variation, such as lighting or camera placement. sites.google.com/view/generaliz… 1/n
    00:00
    33K
  • user avatar
    Lisa Lee
    @rl_agent
    Jul 11, 2018
    I'm excited to present our Gated Path Planning Networks paper at #ICML2018 today. Come say hi! Oral Talk: 14:10 @ A1 Poster: 18:15 - 21:00 @ Hall B #134 Paper: arxiv.org/abs/1806.06408 Code: github.com/lileee/gated-p… - with Emilio, @dchaplot, Eric, @rsalakhu
  • user avatar
    Lisa Lee
    @rl_agent
    Jul 28, 2023
    Our new work is featured in the @nytimes: RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control tl;dr We fine-tune a VLM to predict robot actions directly as text, and see emergent capabilities in the embodied agent. (1/n)
    Aided by A.I. Language Models, Google’s Robots Are Getting Smart (Gift Article)
    From nytimes.com
    28K
  • user avatar
    Lisa Lee
    @rl_agent
    Aug 18, 2023
    Visited @mcgillu in Montreal. Such a beautiful campus in a beautiful city 🇨🇦🍁
    9.2K
  • user avatar
    Lisa Lee
    @rl_agent
    Dec 25, 2019
    Video & slides for LIRE workshop @ #NeurIPS2019 are now up: sites.google.com/view/neurips20… Check out the Talks and Panel by @RaiaHadsell @tommmitchell Jeff Bilmes @pabbeel @YejinChoinka Tom Griffiths & more. Thanks to all speakers & presenters for making the workshop a success!
  • user avatar
    Lisa Lee
    @rl_agent
    Oct 1, 2019
    I just started at Stanford this week as a visiting researcher in @chelseabfinn's lab, and I'm also still part-time at Google Brain Robotics. If you're around in the area and would like to chat about research, please feel free to reach out anytime! (My office is in Gates)