Very excited to present our work “VIABLE: Fast Adaptation via Backpropagating Learned Loss” at NeurIPS Conference Workshop on Meta-Learning - with Luisa Zintgraf, @bei_peng, Shimon Whiteson. Paper: arxiv.org/abs/1911.13159

We're at #NeurIPS2019 🤓🇨🇦 Looking forward to an exciting week! Here's an overview of what we are up to (details in the thread) 👇

“VIABLE: Fast Adaptation via Backpropagating Learned Loss” - Leo Feng, Luisa Zintgraf, @bei_peng, Shimon Whiteson (Workshop on Meta Learning, Sat, Poster session 3:20-4:20 PM, West Ballroom B) Paper: arxiv.org/abs/1911.13159

Better late than never: I'm finally at NeurIPS and am excited about to give an invited talk about Bayes-adaptive deep RL at tomorrow's deep RL workshop, 10am. sites.google.com/view/deep-rl-w…

We are very excited about two accepted ICLR 2026 papers! See you in Ethiopia 🇪🇹🤓😍 Camera ready papers will be out soon.

We're looking forward to an exciting virtual #ICLR2020! 🤩 Starting today with a fantastic day of workshops - meet some of us at the BetrRL workshop or check out the papers / videos in the thread 👇

"Exploration in Approximate Hyper-State Space" Luisa Zintgraf, Leo Feng, Maximilian Igl, Kristian Hartikainen, Katja Hofmann, Shimon Whiteson Link: betr-rl.ml/2020/abs/26/

🙌 I was fortunate to have Luisa Zintgraf as a mentor during my undergrad at Oxford. She encouraged and supported me throughout, from knowing nothing to submitting my first paper and my thesis. I'm extremely grateful for her guidance that inspires me to be a mentor one day. 🙌

I can highly recommend hosting a social if you're attending ICLR - when I hosted one during #WiML last December we had lots of fun! It's a great way to meet new people and make virtual conferences more interactive 🙈😍 *And* you can choose the theme of the social!!

Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning -Luisa Zintgraf, Leo Feng, Cong Lu, Maximilian Igl, Kristian Hartikainen, Katja Hofmann, Shimon Whiteson arxiv.org/pdf/2010.01062…

Really excited about this recent work to feature in #ICML2021 on meta-learning task exploration in agent belief space!

Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning Spotlight: Multitask Learning 1, Thu 5 — 6 pm PDT Poster: Fri 5 — 8 am BST Page: icml.cc/virtual/2021/p… Luisa Zintgraf, Leo Feng, Cong Lu, Maximilian Igl, Kristian Hartikainen, Katja Hofmann, Shimon Whiteson

In Meta-RL, the *agent* is responsible for collecting the data that we meta-train on. If it doesn't do this well, meta-training can fail! 😱 We address this meta-exploration problem in our #ICML2021 paper. Come by our poster this Friday 5-7AM BST!