Levi Lelis
@programsynthesis.bsky.social
Associate Professor - University of Alberta
Canada CIFAR AI Chair with Amii
Machine Learning and Program Synthesis
he/him; ele/dele 🇨🇦 🇧🇷
https://www.cs.ualberta.ca/~santanad
Canada CIFAR AI Chair with Amii
Machine Learning and Program Synthesis
he/him; ele/dele 🇨🇦 🇧🇷
https://www.cs.ualberta.ca/~santanad
Pinned
Levi Lelis
@programsynthesis.bsky.social
· Dec 18
Levi Lelis - Learning Libraries of Programmatic Policies - IPAM at UCLA
YouTube video by Institute for Pure & Applied Mathematics (IPAM)
youtu.be
I recently spoke at IPAM's Naturalistic Approaches to Artificial Intelligence Workshop, sharing some of the programmatic perspectives we're exploring in reinforcement learning research.
youtu.be/UNpg05yxc3o?...
youtu.be/UNpg05yxc3o?...
Reposted by Levi Lelis
Brazil shows how it’s done in a democracy
Brazil’s supreme court finds Bolsonaro guilty of plotting military coup
Former president faces decades-long jail sentence for seeking to forcibly cling to power after losing 2022 election
www.theguardian.com
September 11, 2025 at 8:37 PM
Brazil shows how it’s done in a democracy
Reposted by Levi Lelis
Excited to announce that our work on Reinforcement Learning for Arachnophobia treatment has been accepted at ACM Transactions on Interactive Intelligent Systems! We found that an RL agent could more effectively adapt VR spiders to achieve specified anxiety levels in users compared to current SOTA.
August 25, 2025 at 1:39 AM
Excited to announce that our work on Reinforcement Learning for Arachnophobia treatment has been accepted at ACM Transactions on Interactive Intelligent Systems! We found that an RL agent could more effectively adapt VR spiders to achieve specified anxiety levels in users compared to current SOTA.
Reposted by Levi Lelis
Was talking to a student who wasn't sure about why one would get a PhD. So I wrote up a list of reasons!
www.eugenevinitsky.com/posts/reason...
www.eugenevinitsky.com/posts/reason...
Eugene Vinitsky
www.eugenevinitsky.com
July 27, 2025 at 7:30 PM
Was talking to a student who wasn't sure about why one would get a PhD. So I wrote up a list of reasons!
www.eugenevinitsky.com/posts/reason...
www.eugenevinitsky.com/posts/reason...
Reposted by Levi Lelis
Previous work has shown that programmatic policies—computer programs written in a domain-specific language—generalize to out-of-distribution problems more easily than neural policies.
Is this really the case? 🧵
Is this really the case? 🧵
July 2, 2025 at 10:12 PM
Previous work has shown that programmatic policies—computer programs written in a domain-specific language—generalize to out-of-distribution problems more easily than neural policies.
Is this really the case? 🧵
Is this really the case? 🧵
Previous work has shown that programmatic policies—computer programs written in a domain-specific language—generalize to out-of-distribution problems more easily than neural policies.
Is this really the case? 🧵
Is this really the case? 🧵
July 2, 2025 at 10:12 PM
Previous work has shown that programmatic policies—computer programs written in a domain-specific language—generalize to out-of-distribution problems more easily than neural policies.
Is this really the case? 🧵
Is this really the case? 🧵
Reposted by Levi Lelis
If like me your Discover feed has been even worse lately and you are here for ML/AI news and discussion, check out these two feeds:
- Paper Skygest
- ML Feed: Trending
Links below 👇
- Paper Skygest
- ML Feed: Trending
Links below 👇
June 29, 2025 at 1:26 AM
If like me your Discover feed has been even worse lately and you are here for ML/AI news and discussion, check out these two feeds:
- Paper Skygest
- ML Feed: Trending
Links below 👇
- Paper Skygest
- ML Feed: Trending
Links below 👇
Reposted by Levi Lelis
As AI agents face increasingly long and complex tasks, decomposing them into subtasks becomes increasingly appealing.
But how do we discover such temporal structure?
Hierarchical RL provides a natural formalism-yet many questions remain open.
Here's our overview of the field🧵
But how do we discover such temporal structure?
Hierarchical RL provides a natural formalism-yet many questions remain open.
Here's our overview of the field🧵
June 27, 2025 at 8:16 PM
As AI agents face increasingly long and complex tasks, decomposing them into subtasks becomes increasingly appealing.
But how do we discover such temporal structure?
Hierarchical RL provides a natural formalism-yet many questions remain open.
Here's our overview of the field🧵
But how do we discover such temporal structure?
Hierarchical RL provides a natural formalism-yet many questions remain open.
Here's our overview of the field🧵
Reposted by Levi Lelis
As hot as this summer is, it’s also one of the coolest we’ll ever enjoy again.
Just how much hotter and deadlier summers will get is still up to us. Right now we’re working hard to make them worse
🎁 link to my @opinion.bloomberg.com column:
www.bloomberg.com/opinion/arti...
Just how much hotter and deadlier summers will get is still up to us. Right now we’re working hard to make them worse
🎁 link to my @opinion.bloomberg.com column:
www.bloomberg.com/opinion/arti...
The Heat Dome Wants a Word With Climate-Change Deniers
The temperatures gripping the US this week were made up to five times more likely by the fact that the atmosphere is simply hotter.
www.bloomberg.com
June 24, 2025 at 12:32 PM
As hot as this summer is, it’s also one of the coolest we’ll ever enjoy again.
Just how much hotter and deadlier summers will get is still up to us. Right now we’re working hard to make them worse
🎁 link to my @opinion.bloomberg.com column:
www.bloomberg.com/opinion/arti...
Just how much hotter and deadlier summers will get is still up to us. Right now we’re working hard to make them worse
🎁 link to my @opinion.bloomberg.com column:
www.bloomberg.com/opinion/arti...
Reposted by Levi Lelis
Hiring a postdoc to scale up and deploy RL-based planning onto some self-driving cars! We'll be building on arxiv.org/abs/2502.03349 and learn what the limits and challenges of RL planning are. Shoot me a message if interested and help spread the word please!
Full posting to come in a bit.
Full posting to come in a bit.
Robust Autonomy Emerges from Self-Play
Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...
arxiv.org
June 21, 2025 at 5:14 PM
Hiring a postdoc to scale up and deploy RL-based planning onto some self-driving cars! We'll be building on arxiv.org/abs/2502.03349 and learn what the limits and challenges of RL planning are. Shoot me a message if interested and help spread the word please!
Full posting to come in a bit.
Full posting to come in a bit.
Reposted by Levi Lelis
We’re extending the AIIDE deadline! Partially due to author requests, partially due to a significant increase in submissions meaning I need to increase the PC!
🚨#AIIDE25 full paper deadline extended!
Due to requests from authors, we have extended the deadline for full paper submission to June 27, 2025!
🔗 More information: sites.google.com/ualberta.ca/...
Due to requests from authors, we have extended the deadline for full paper submission to June 27, 2025!
🔗 More information: sites.google.com/ualberta.ca/...
AIIDE 2025 - Call for Papers
AIIDE 2025 welcomes submissions across the vast field of Artificial Intelligence and Interactive Digital Entertainment. We are particularly interested in novel contributions and applications, as well ...
sites.google.com
June 16, 2025 at 6:21 PM
We’re extending the AIIDE deadline! Partially due to author requests, partially due to a significant increase in submissions meaning I need to increase the PC!
🧵1/ New paper! 📄 Subgoal-Guided Policy Heuristic Search with Learned Subgoals, led by my PhD student @tuero.ca.
arxiv.org/pdf/2506.07255
This paper follows the Levin tree search (LTS) research line and focuses on learning subgoal-based policies.
arxiv.org/pdf/2506.07255
This paper follows the Levin tree search (LTS) research line and focuses on learning subgoal-based policies.
June 13, 2025 at 3:29 AM
🧵1/ New paper! 📄 Subgoal-Guided Policy Heuristic Search with Learned Subgoals, led by my PhD student @tuero.ca.
arxiv.org/pdf/2506.07255
This paper follows the Levin tree search (LTS) research line and focuses on learning subgoal-based policies.
arxiv.org/pdf/2506.07255
This paper follows the Levin tree search (LTS) research line and focuses on learning subgoal-based policies.
I enjoyed reading this and the comments within it.
Does everyone in your community agree on some folk knowledge that isn’t published anywhere? Put it in a paper! It’s a pretty valuable contribution
June 12, 2025 at 4:06 AM
I enjoyed reading this and the comments within it.
Reposted by Levi Lelis
After literal years of being down due to security issues, my blog is now back up, including my one post on "How to Write an AIIDE Paper" www.guzdial.com/blog/how-to-...
How to Write an AIIDE Paper – Matthew Guzdial Blog
www.guzdial.com
June 6, 2025 at 8:45 PM
After literal years of being down due to security issues, my blog is now back up, including my one post on "How to Write an AIIDE Paper" www.guzdial.com/blog/how-to-...
Reposted by Levi Lelis
We are very happy to report that the second edition of our textbook on Artificial Intelligence and Games is now finally published! This book is a thorough update of our popular textbook, trying to provide a comprehensive coverage of the many aspects of and use cases for AI in games.
June 3, 2025 at 3:17 PM
We are very happy to report that the second edition of our textbook on Artificial Intelligence and Games is now finally published! This book is a thorough update of our popular textbook, trying to provide a comprehensive coverage of the many aspects of and use cases for AI in games.
Reposted by Levi Lelis
Excited to announce that the second edition of the PCGML textbook by @sampsnodgrass.bsky.social, @autumnsburg.bsky.social, and myself is up!
This version is a major update of the first, with a new chapter on GenAI and updates on the last two years of research.
link.springer.com/book/10.1007...
This version is a major update of the first, with a new chapter on GenAI and updates on the last two years of research.
link.springer.com/book/10.1007...
Procedural Content Generation via Machine Learning
This book updates and expands upon the first beginner-focused guide to procedural content generation via machine learning (PCGML)
link.springer.com
May 30, 2025 at 3:44 PM
Excited to announce that the second edition of the PCGML textbook by @sampsnodgrass.bsky.social, @autumnsburg.bsky.social, and myself is up!
This version is a major update of the first, with a new chapter on GenAI and updates on the last two years of research.
link.springer.com/book/10.1007...
This version is a major update of the first, with a new chapter on GenAI and updates on the last two years of research.
link.springer.com/book/10.1007...
We have extended the submission deadlines for these workshops.
Programmatic Representations for Agent Learning (ICML) - Vancouver.
- Deadline: May 30, 2025 (pral-workshop.github.io)
Programmatic Reinforcement Learning (RLC) - Edmonton.
- Deadline: June 6, 2025 (prl-workshop.github.io)
Programmatic Representations for Agent Learning (ICML) - Vancouver.
- Deadline: May 30, 2025 (pral-workshop.github.io)
Programmatic Reinforcement Learning (RLC) - Edmonton.
- Deadline: June 6, 2025 (prl-workshop.github.io)
May 28, 2025 at 5:15 PM
We have extended the submission deadlines for these workshops.
Programmatic Representations for Agent Learning (ICML) - Vancouver.
- Deadline: May 30, 2025 (pral-workshop.github.io)
Programmatic Reinforcement Learning (RLC) - Edmonton.
- Deadline: June 6, 2025 (prl-workshop.github.io)
Programmatic Representations for Agent Learning (ICML) - Vancouver.
- Deadline: May 30, 2025 (pral-workshop.github.io)
Programmatic Reinforcement Learning (RLC) - Edmonton.
- Deadline: June 6, 2025 (prl-workshop.github.io)
Reposted by Levi Lelis
📢 I'm very excited to release AgarCL, a new evaluation platform for research in continual reinforcement learning‼️
Repo: github.com/machado-rese...
Website: agarcl.github.io
Preprint: arxiv.org/abs/2505.18347
Details below 👇
Repo: github.com/machado-rese...
Website: agarcl.github.io
Preprint: arxiv.org/abs/2505.18347
Details below 👇
May 27, 2025 at 3:48 AM
📢 I'm very excited to release AgarCL, a new evaluation platform for research in continual reinforcement learning‼️
Repo: github.com/machado-rese...
Website: agarcl.github.io
Preprint: arxiv.org/abs/2505.18347
Details below 👇
Repo: github.com/machado-rese...
Website: agarcl.github.io
Preprint: arxiv.org/abs/2505.18347
Details below 👇
Reposted by Levi Lelis
🧵1/ New paper! 📄 InnateCoder: Learning Programmatic Options with Foundation Models
This is Rubens Moraes' final chapter of his PhD thesis from Universidade Federal de Viçosa, Brazil, in collaboration with Quazi Sadmine and Hendrik Baier.
arXiv: arxiv.org/abs/2505.12508
This is Rubens Moraes' final chapter of his PhD thesis from Universidade Federal de Viçosa, Brazil, in collaboration with Quazi Sadmine and Hendrik Baier.
arXiv: arxiv.org/abs/2505.12508
May 23, 2025 at 8:31 PM
🧵1/ New paper! 📄 InnateCoder: Learning Programmatic Options with Foundation Models
This is Rubens Moraes' final chapter of his PhD thesis from Universidade Federal de Viçosa, Brazil, in collaboration with Quazi Sadmine and Hendrik Baier.
arXiv: arxiv.org/abs/2505.12508
This is Rubens Moraes' final chapter of his PhD thesis from Universidade Federal de Viçosa, Brazil, in collaboration with Quazi Sadmine and Hendrik Baier.
arXiv: arxiv.org/abs/2505.12508
Reposted by Levi Lelis
📢 I'm happy to share the preprint: _Reward-Aware Proto-Representations in Reinforcement Learning_ ‼️
My PhD student, Hon Tik Tse, led this work, and my MSc student, Siddarth Chandrasekar, assisted us.
arxiv.org/abs/2505.16217
Basically, it's the SR with rewards. See below 👇
My PhD student, Hon Tik Tse, led this work, and my MSc student, Siddarth Chandrasekar, assisted us.
arxiv.org/abs/2505.16217
Basically, it's the SR with rewards. See below 👇
May 24, 2025 at 3:23 PM
📢 I'm happy to share the preprint: _Reward-Aware Proto-Representations in Reinforcement Learning_ ‼️
My PhD student, Hon Tik Tse, led this work, and my MSc student, Siddarth Chandrasekar, assisted us.
arxiv.org/abs/2505.16217
Basically, it's the SR with rewards. See below 👇
My PhD student, Hon Tik Tse, led this work, and my MSc student, Siddarth Chandrasekar, assisted us.
arxiv.org/abs/2505.16217
Basically, it's the SR with rewards. See below 👇
🧵1/ New paper! 📄 InnateCoder: Learning Programmatic Options with Foundation Models
This is Rubens Moraes' final chapter of his PhD thesis from Universidade Federal de Viçosa, Brazil, in collaboration with Quazi Sadmine and Hendrik Baier.
arXiv: arxiv.org/abs/2505.12508
This is Rubens Moraes' final chapter of his PhD thesis from Universidade Federal de Viçosa, Brazil, in collaboration with Quazi Sadmine and Hendrik Baier.
arXiv: arxiv.org/abs/2505.12508
May 23, 2025 at 8:31 PM
🧵1/ New paper! 📄 InnateCoder: Learning Programmatic Options with Foundation Models
This is Rubens Moraes' final chapter of his PhD thesis from Universidade Federal de Viçosa, Brazil, in collaboration with Quazi Sadmine and Hendrik Baier.
arXiv: arxiv.org/abs/2505.12508
This is Rubens Moraes' final chapter of his PhD thesis from Universidade Federal de Viçosa, Brazil, in collaboration with Quazi Sadmine and Hendrik Baier.
arXiv: arxiv.org/abs/2505.12508
Reposted by Levi Lelis
🎉 Super excited: today @sharky6000.bsky.social is presenting our new algorithm Progressive Hiding at #AAMAS2025!
It's a learning method for games with imperfect information.
🔗 See his post: bsky.app/profile/shar...
Wish I could be there! 😢 1/6
It's a learning method for games with imperfect information.
🔗 See his post: bsky.app/profile/shar...
Wish I could be there! 😢 1/6
Day #5 and last day 😭 @aamasconf.bsky.social
We'll be presenting one more paper called "Learning in Games with Progressive Hiding" by @benhey.bsky.social and myself.
Poster @ 10am, talk @ 11:30am.
arxiv.org/abs/2409.03875
This is an application of progressive hedging to learning in games:
1/2
We'll be presenting one more paper called "Learning in Games with Progressive Hiding" by @benhey.bsky.social and myself.
Poster @ 10am, talk @ 11:30am.
arxiv.org/abs/2409.03875
This is an application of progressive hedging to learning in games:
1/2
May 23, 2025 at 1:28 PM
🎉 Super excited: today @sharky6000.bsky.social is presenting our new algorithm Progressive Hiding at #AAMAS2025!
It's a learning method for games with imperfect information.
🔗 See his post: bsky.app/profile/shar...
Wish I could be there! 😢 1/6
It's a learning method for games with imperfect information.
🔗 See his post: bsky.app/profile/shar...
Wish I could be there! 😢 1/6
Are you interested in programmatic representations in machine learning? Please consider submitting your work to these workshops: one at ICML and another at RLC. 🧵
May 21, 2025 at 4:23 AM
Are you interested in programmatic representations in machine learning? Please consider submitting your work to these workshops: one at ICML and another at RLC. 🧵
Wow! Great list of papers on the computational capability of neural networks.
Computational Capability and Efficiency of Neural Networks: A Repository of Papers
I compiled a list of theoretical papers related to the computational capabilities of Transformers, recurrent networks, feedforward networks, and graph neural networks.
Link: github.com/opallab/neur...
I compiled a list of theoretical papers related to the computational capabilities of Transformers, recurrent networks, feedforward networks, and graph neural networks.
Link: github.com/opallab/neur...
May 17, 2025 at 4:53 AM
Wow! Great list of papers on the computational capability of neural networks.
Reposted by Levi Lelis
🎓 PhD position available!
Join our interdisciplinary research project on causal agent-based modelling!
🔍 Looking for curious minds with a MSc degree (or near to completing one) in CS/AI/related fields.
📍 Location: Utrecht University, NL
🗓️ Deadline: 16 June 2025
📩 Info: www.uu.nl/en/organisat...
Join our interdisciplinary research project on causal agent-based modelling!
🔍 Looking for curious minds with a MSc degree (or near to completing one) in CS/AI/related fields.
📍 Location: Utrecht University, NL
🗓️ Deadline: 16 June 2025
📩 Info: www.uu.nl/en/organisat...
PhD Position in Causal Agent-based Modelling of Complex Social Systems
Join this exciting interdisciplinary research project at the Centre for Complex Systems Studies and study causal agent-based modelling!
www.uu.nl
May 13, 2025 at 7:31 PM
🎓 PhD position available!
Join our interdisciplinary research project on causal agent-based modelling!
🔍 Looking for curious minds with a MSc degree (or near to completing one) in CS/AI/related fields.
📍 Location: Utrecht University, NL
🗓️ Deadline: 16 June 2025
📩 Info: www.uu.nl/en/organisat...
Join our interdisciplinary research project on causal agent-based modelling!
🔍 Looking for curious minds with a MSc degree (or near to completing one) in CS/AI/related fields.
📍 Location: Utrecht University, NL
🗓️ Deadline: 16 June 2025
📩 Info: www.uu.nl/en/organisat...
I enjoyed reading this thread.
Solving Single Agent Fully Observable Deterministic (SAFODP) Problems with Dec-POMDP approaches #SundayHarangue #allegory
x.com/rao2z/status...
x.com/rao2z/status...
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు) on X: "Solving Single Agent Fully Observable Deterministic (SAFODP) Problems with Dec-POMDP approaches #SundayHarangue #allegory Imagine you modeled your decision problem into a Dec-POMDP problem ('cuz that's as expressive a decision model as you can get! )--but with some https://t.co/vDWYTHbnQA" / X
Solving Single Agent Fully Observable Deterministic (SAFODP) Problems with Dec-POMDP approaches #SundayHarangue #allegory Imagine you modeled your decision problem into a Dec-POMDP problem ('cuz that's as expressive a decision model as you can get! )--but with some https://t.co/vDWYTHbnQA
x.com
May 12, 2025 at 3:06 AM
I enjoyed reading this thread.