Glen Berseth
@glenberseth.bsky.social
Assistant Prof at @UMontreal @mila-quebec.bsky.social @MontrealRobots
. CIFAR AI Chair, RL_Conference chair. Creating generalist problem-solving agents for the real world. He/him/il.
. CIFAR AI Chair, RL_Conference chair. Creating generalist problem-solving agents for the real world. He/him/il.
Pinned
Glen Berseth
@glenberseth.bsky.social
· Oct 8
Creating Generalist robotics policies (GRPs) is tricky. In this video (and code) I share how to create a GRP from scratch from some basic transformer code. This is the first step in my plan to create a course on large models and scaling for RL and Robotics.
I have updated my tutorial on making Vision Language Action models. This tutorial starts with a basic Transformer and walks people through the steps to transform it into a full VLA that uses PaliGemma as the pretrained VLM. Links below.
February 9, 2026 at 2:15 PM
I have updated my tutorial on making Vision Language Action models. This tutorial starts with a basic Transformer and walks people through the steps to transform it into a full VLA that uses PaliGemma as the pretrained VLM. Links below.
I am looking forward to our first round of speakers tomorrow at @Mila_Quebec #worldmodels workshop.
world-model-mila.github.io
world-model-mila.github.io
February 3, 2026 at 8:49 PM
I am looking forward to our first round of speakers tomorrow at @Mila_Quebec #worldmodels workshop.
world-model-mila.github.io
world-model-mila.github.io
How, after billions of dollars spent on code generation tool development they still can't reliably generate a working Dockerfile...
January 14, 2026 at 4:11 AM
How, after billions of dollars spent on code generation tool development they still can't reliably generate a working Dockerfile...
I am finally fully benefiting from making my lecture content in LaTeX. Creating new content powered by LLMs to make examples and translate my content to a webpage and a book is a breeze. Just need to figure out how to add references faster.
January 9, 2026 at 3:00 AM
I am finally fully benefiting from making my lecture content in LaTeX. Creating new content powered by LLMs to make examples and translate my content to a webpage and a book is a breeze. Just need to figure out how to add references faster.
Reposted by Glen Berseth
Reinforcement Learning Conference (RLC) was added to the AI conference DL countdown.
rl-conference.cc
March 1: Abstract DL (AoE)
March 5: Submission DL (AoE)
Conference: Montreal, Quebec, Canada,
August 16th -19th, 2026.
rl-conference.cc
March 1: Abstract DL (AoE)
March 5: Submission DL (AoE)
Conference: Montreal, Quebec, Canada,
August 16th -19th, 2026.
January 7, 2026 at 10:11 AM
Reinforcement Learning Conference (RLC) was added to the AI conference DL countdown.
rl-conference.cc
March 1: Abstract DL (AoE)
March 5: Submission DL (AoE)
Conference: Montreal, Quebec, Canada,
August 16th -19th, 2026.
rl-conference.cc
March 1: Abstract DL (AoE)
March 5: Submission DL (AoE)
Conference: Montreal, Quebec, Canada,
August 16th -19th, 2026.
Another exciting year for more RL! Submit your work to the RL conference and join us to talk a out how to make RL even better.
Hi RL Enthusiasts!
RLC is coming to Montreal, Quebec, in the summer: Aug 16–19, 2026!
Call for Papers is up now:
Abstract: Mar 1 (AOE)
Submission: Mar 5 (AOE)
Excited to see what you’ve been up to - Submit your best work!
rl-conference.cc/callforpaper...
Please share widely!
RLC is coming to Montreal, Quebec, in the summer: Aug 16–19, 2026!
Call for Papers is up now:
Abstract: Mar 1 (AOE)
Submission: Mar 5 (AOE)
Excited to see what you’ve been up to - Submit your best work!
rl-conference.cc/callforpaper...
Please share widely!
RLJ | RLC Call for Papers
rl-conference.cc
December 24, 2025 at 1:21 PM
Another exciting year for more RL! Submit your work to the RL conference and join us to talk a out how to make RL even better.
I'll be giving a talk tomorrow in the Embodied World Models for Decision Making workshop at #NeurIPS. I will present a number of recent works from my lab on combining foundational models with planning and RL.
When: 11:30-noon
Where: Level Room 30A-E
When: 11:30-noon
Where: Level Room 30A-E
December 6, 2025 at 7:27 PM
I'll be giving a talk tomorrow in the Embodied World Models for Decision Making workshop at #NeurIPS. I will present a number of recent works from my lab on combining foundational models with planning and RL.
When: 11:30-noon
Where: Level Room 30A-E
When: 11:30-noon
Where: Level Room 30A-E
#VisionLanguage models are increasingly used for a wide range of problems, but seem complex to build. I wrote some code and recorded a tutorial in my lab yesterday to help others demystify how to create these models. #keepbuilding
November 25, 2025 at 5:40 PM
#VisionLanguage models are increasingly used for a wide range of problems, but seem complex to build. I wrote some code and recorded a tutorial in my lab yesterday to help others demystify how to create these models. #keepbuilding
My lab is looking for new students who are very passionate about foundational models and planning/RL/robotics. Apply via Mila. I will also be at #NeurIPS to discuss research ideas and opportunities. See notes below for application advice.
November 19, 2025 at 3:10 PM
My lab is looking for new students who are very passionate about foundational models and planning/RL/robotics. Apply via Mila. I will also be at #NeurIPS to discuss research ideas and opportunities. See notes below for application advice.
This not only seems illegal but is a breach of the social contract and trust in this research system. I can't see any good reason for breaking the confidentially of research grants and reference letters.
Canadian researchers should be aware the there is a motion before the Parliamentary Standing Committee on Science and Research to force Tricouncils to hand over disaggregated peer review data on all applications:
Applicant names, profiles, demographics
Reviewers names, profiles, comments, and scores
Applicant names, profiles, demographics
Reviewers names, profiles, comments, and scores
October 31, 2025 at 2:55 PM
This not only seems illegal but is a breach of the social contract and trust in this research system. I can't see any good reason for breaking the confidentially of research grants and reference letters.
@pcastr.bsky.social is adding good clarity to the challenges of deep RL. Awesome stuff.
🚨The Formalism-Implementation Gap in RL research🚨
Lots of progress in RL research over last 10 years, but too much performance-driven => overfitting to benchmarks (like the ALE).
1⃣ Let's advance science of RL
2⃣ Let's be explicit about how benchmarks map to formalism
1/X
Lots of progress in RL research over last 10 years, but too much performance-driven => overfitting to benchmarks (like the ALE).
1⃣ Let's advance science of RL
2⃣ Let's be explicit about how benchmarks map to formalism
1/X
October 28, 2025 at 6:15 PM
@pcastr.bsky.social is adding good clarity to the challenges of deep RL. Awesome stuff.
I have been seeing the subtleties in this race play out as destroying relationships. Families can fall apart because of the pressure to keep going in this race. Take care of yourselves everyone.
October 25, 2025 at 6:08 PM
I have been seeing the subtleties in this race play out as destroying relationships. Families can fall apart because of the pressure to keep going in this race. Take care of yourselves everyone.
Does anyone in this universe know which human being accepts join requests for the #mlnews ml-news Google group? groups.google.com/g/ml-news. It says "This group is moderated and maintained by IMLS (www.machinelearning.org)." but that link just goes to the ICML webpage...
Machine Learning News - Google Groups
groups.google.com
October 19, 2025 at 9:55 PM
Does anyone in this universe know which human being accepts join requests for the #mlnews ml-news Google group? groups.google.com/g/ml-news. It says "This group is moderated and maintained by IMLS (www.machinelearning.org)." but that link just goes to the ICML webpage...
Surprise/empowerment/etc may be the fundamental objectives living organisms optimize, however it is very difficult to optimize these objectives. I will be giving a talk at international worlshop on #activeinference on how foundational models can help improve these methods.
October 17, 2025 at 3:13 PM
Surprise/empowerment/etc may be the fundamental objectives living organisms optimize, however it is very difficult to optimize these objectives. I will be giving a talk at international worlshop on #activeinference on how foundational models can help improve these methods.
For those interested in joining my lab, submit your application via the Mila form. This year I am particularly interested in students with skills/interests in robotics, reinforcement learning and, foundational models which will push forward the abilities of real world agents.
October 15, 2025 at 1:02 PM
For those interested in joining my lab, submit your application via the Mila form. This year I am particularly interested in students with skills/interests in robotics, reinforcement learning and, foundational models which will push forward the abilities of real world agents.
I am at #COLM2025 today to talk about AI, LLMs and simulation in the social simulation workshop. Come find me, happy to chat about all things AI, embodiment, and simulation.
October 10, 2025 at 2:50 PM
I am at #COLM2025 today to talk about AI, LLMs and simulation in the social simulation workshop. Come find me, happy to chat about all things AI, embodiment, and simulation.
The same could be said for science.
The single biggest epistemic challenge in the internet era is remaining calibrated about what "normal" people think while the internet throws up an infinite wall of crazy. Thousands of people sharing an absurd opinion on the internet tells you very little!
October 2, 2025 at 2:21 PM
The same could be said for science.
GRPO is more like REINFORCE than PPO.
1) It does not train a critic (no need with small variance)
2) The SCORE FUNCTION (difficult to call this an advantage) is over a batch using the same initial prompt (similar to the vine sample method from TRPO)
1) It does not train a critic (no need with small variance)
2) The SCORE FUNCTION (difficult to call this an advantage) is over a batch using the same initial prompt (similar to the vine sample method from TRPO)
October 1, 2025 at 12:49 AM
GRPO is more like REINFORCE than PPO.
1) It does not train a critic (no need with small variance)
2) The SCORE FUNCTION (difficult to call this an advantage) is over a batch using the same initial prompt (similar to the vine sample method from TRPO)
1) It does not train a critic (no need with small variance)
2) The SCORE FUNCTION (difficult to call this an advantage) is over a batch using the same initial prompt (similar to the vine sample method from TRPO)
On my way to South Korea for a week packed with robotics at the conference on Robot Learning, Humanoids2025, and the global forum on mechanical engineering.
September 24, 2025 at 12:23 PM
On my way to South Korea for a week packed with robotics at the conference on Robot Learning, Humanoids2025, and the global forum on mechanical engineering.
One of the most common logical fallacies I see is "GPUs are cooking, therefore progress." I see people with 1/10th the compute get 10x more progress because... they have a more thorough plan. #Moretimethinkinglesstimeburning
September 22, 2025 at 1:14 AM
One of the most common logical fallacies I see is "GPUs are cooking, therefore progress." I see people with 1/10th the compute get 10x more progress because... they have a more thorough plan. #Moretimethinkinglesstimeburning
I suggest going out and talking to real people. They provide a much richer signal.
The single biggest epistemic challenge in the internet era is remaining calibrated about what "normal" people think while the internet throws up an infinite wall of crazy. Thousands of people sharing an absurd opinion on the internet tells you very little!
September 8, 2025 at 9:30 PM
I suggest going out and talking to real people. They provide a much richer signal.
VLAs offer an avenue for generalist robot policies; however, naively following the action predictions leads to brittle or unsafe behaviours. We introduce VLAPS, which integrates model-based search with pre-trained VLA policies to improve performance without additional training.
August 23, 2025 at 5:52 PM
VLAs offer an avenue for generalist robot policies; however, naively following the action predictions leads to brittle or unsafe behaviours. We introduce VLAPS, which integrates model-based search with pre-trained VLA policies to improve performance without additional training.
Efficiency may be the most important. If we can't make these tools economical, they will not last.
AI efficiency is important. The median Gemini Apps text prompt in May 2025 used 0.24 Wh of energy (<9 seconds of TV watching) & 0.26 mL (~5 drops) of water. Over 12 months, we reduced the energy footprint of a median text prompt 33x, while improving quality:
cloud.google.com/blog/product...
cloud.google.com/blog/product...
August 21, 2025 at 10:22 PM
Efficiency may be the most important. If we can't make these tools economical, they will not last.
My lab at @montrealrobotics.bsky.social was honoured to present our recent work to @mark-carney.bsky.social and Even Solomon explaining how AI enables new robotics that will drive innovation in Canada. It was a pleasure getting into the details with a quick dive into deterministic policy gradients!
August 20, 2025 at 10:59 PM
My lab at @montrealrobotics.bsky.social was honoured to present our recent work to @mark-carney.bsky.social and Even Solomon explaining how AI enables new robotics that will drive innovation in Canada. It was a pleasure getting into the details with a quick dive into deterministic policy gradients!
Another fantastic Montreal Robotics Summer School! Thanks to our sponsors, organizers, and @mila-quebec.bsky.social, we doubled in size this year. Congratulations again to all the students who make this school happen, and for your progress in machine learning and robotics.
August 17, 2025 at 2:23 PM
Another fantastic Montreal Robotics Summer School! Thanks to our sponsors, organizers, and @mila-quebec.bsky.social, we doubled in size this year. Congratulations again to all the students who make this school happen, and for your progress in machine learning and robotics.