Policy-Induced Self-Supervision for RL - February 15, 2023
What makes for good representations in visual RL? We study this question in our new preprint, and propose a simple change on top of vision SSL objectives to tailor them to RL finetuning.
[ ArXiv, pdf, website]
New paper on lifelong learning - January 20, 2023
Our preprint benchmarking a wide range of lifelong learning agents is out! Hat tip to Megan Baker who coordinate the effort of 47(!) contributors. [ ArXiv, pdf, ScienceDirect]
Thesis defended! - December 5, 2022
I successfully defended my thesis titled Quickly solving new tasks, with meta-learning and without. Many thanks to my committee:
Fei Sha, Maja Matarić, Salman Avestimehr, Jesse Thomason, and Stefanos Nikolaidis.
Policy Learning and Evaluation with RQMC - February 21, 2022
Our paper Policy Learning and Evaluation with Randomized Quasi-Monte Carlo will be presented at AISTATS’22. [ArXiv, pdf, web, code]
Summer at Google Research - January 19, 2022
I look forward to spending the summer at Google Research in Mountain View, CA with Ice Pasupat, Kelvin Guu, and Vincent Zhao.
EPFL’s NeurIPS Mirror Event - December 3, 2021
I’ll give a short talk and present the poster of our Uniform Sampling paper at the EPFL NeurIPS Mirror event. Reach out if you will attend too! [slides, poster]
NeurIPS’21 Outstanding Reviewer Award - October 15, 2021
Delighted to be nominated as an outstanding reviewer for NeurIPS’21.
Uniform Sampling over Episode Difficulty - August 12, 2021
Following my 2020 Amazon internship, our preprint Uniform Sampling over Episode Difficulty is available on ArXiv. [ArXiv, pdf, web, code]
2021/09/28 Update: Accepted as a Spotlight to NeurIPS’21!
Summer at Amazon Prime - April 23, 2021
I will be spending another summer at Amazon, with the Prime team in Seattle, WA.
When MAML Can Adapt Fast and How to Assist When It Cannot - January 22, 2021
Our manuscript on When MAML Can Adapt Fast and How to Assist When It Cannot was accepted at AISTATS 2021. Open-source implementation in learn2learn is now available.
[ArXiv, pdf, web, code]
Summer at Amazon AI - April 1, 2020
I will be spending the summer at Amazon AI in Pasadena, CA.
Decoupling Adaptation from Modeling with Meta-Optimizers - November 17, 2019
Our preprint on Decoupling Adaptation from Modeling with Meta-Optimizers for Meta-Learning is available on ArXiv. Open-source implementation in learn2learn coming soon! [ArXiv, pdf]
Variance of Policy Gradient - November 17, 2019
Our preprint on Analyzing the variance of policy gradient estimators for LQR was accepted at the OptRL NeurIPS workshop. [ArXiv, pdf]
Implicit Gradient Transport - September 5, 2019
Our paper on Reducing the variance in online optimization by transporting past gradients was accepted at NeurIPS as a spotlight contribution. [ArXiv, pdf, website, code]
Open-Sourcing learn2learn - August 20, 2019
Our submission to the PyTorch Summer Hackathon won best in show! Check out the website to learn how to easily implement meta-learning algorithms with learn2learn. [website, code]
East European Summer School - June 5, 2019
I will be attending the East-European Summer School this summer. Get in touch if you will too!
Edit: My poster got lucky and received the best theory poster award!