Jesse Farebrother
@brosa.ca
Ph.D. Student studying AI & decision making at Mila / McGill University. Currently at FAIR @ Meta. Previously Google DeepMind & Google Brain.
https://brosa.ca
https://brosa.ca
Sadly the debugger is missing many nice-to-have features. I wrote a much improved debugger for Jax you can install here: github.com/JesseFarebro... which will probably give you a much better experience 🙂
GitHub - JesseFarebro/xtils: A collection of utilities for machine learning experiments.
A collection of utilities for machine learning experiments. - JesseFarebro/xtils
github.com
May 6, 2025 at 12:25 AM
Sadly the debugger is missing many nice-to-have features. I wrote a much improved debugger for Jax you can install here: github.com/JesseFarebro... which will probably give you a much better experience 🙂
3) At the World Models workshop, I'll be giving an oral on a new approach to learning a generative model of successor states through flow matching / diffusion.
📍Peridot 201 & 206
📅Mon 28 Apr 5 PM - 5:30 PM
Check out the paper on arXiv: arxiv.org/abs/2503.09817 with a full thread coming soon 🙂.
📍Peridot 201 & 206
📅Mon 28 Apr 5 PM - 5:30 PM
Check out the paper on arXiv: arxiv.org/abs/2503.09817 with a full thread coming soon 🙂.
April 22, 2025 at 9:26 PM
3) At the World Models workshop, I'll be giving an oral on a new approach to learning a generative model of successor states through flow matching / diffusion.
📍Peridot 201 & 206
📅Mon 28 Apr 5 PM - 5:30 PM
Check out the paper on arXiv: arxiv.org/abs/2503.09817 with a full thread coming soon 🙂.
📍Peridot 201 & 206
📅Mon 28 Apr 5 PM - 5:30 PM
Check out the paper on arXiv: arxiv.org/abs/2503.09817 with a full thread coming soon 🙂.
2) Arnav & I will be around presenting our work on successor feature matching at:
📍Hall 3 + Hall 2B #572
📅Sat 26 Apr 10 AM — 12:30 PM
Check out the website and paper: arnavkj1995.github.io/SFM/
📍Hall 3 + Hall 2B #572
📅Sat 26 Apr 10 AM — 12:30 PM
Check out the website and paper: arnavkj1995.github.io/SFM/
Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
arnavkj1995.github.io
April 22, 2025 at 9:26 PM
2) Arnav & I will be around presenting our work on successor feature matching at:
📍Hall 3 + Hall 2B #572
📅Sat 26 Apr 10 AM — 12:30 PM
Check out the website and paper: arnavkj1995.github.io/SFM/
📍Hall 3 + Hall 2B #572
📅Sat 26 Apr 10 AM — 12:30 PM
Check out the website and paper: arnavkj1995.github.io/SFM/
1) Many of the team members will be around the poster for Meta Motivo at:
📍Hall 3 + Hall 2B #555
📅 Thu 24 Apr 10 AM — 12:30 PM
Don't forget to check out the demo for yourself: metamotivo.metademolab.com and the paper now on arXiv: arxiv.org/abs/2504.11054
📍Hall 3 + Hall 2B #555
📅 Thu 24 Apr 10 AM — 12:30 PM
Don't forget to check out the demo for yourself: metamotivo.metademolab.com and the paper now on arXiv: arxiv.org/abs/2504.11054
Meta Motivo
A first-of-its-kind behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.
metamotivo.metademolab.com
April 22, 2025 at 9:26 PM
1) Many of the team members will be around the poster for Meta Motivo at:
📍Hall 3 + Hall 2B #555
📅 Thu 24 Apr 10 AM — 12:30 PM
Don't forget to check out the demo for yourself: metamotivo.metademolab.com and the paper now on arXiv: arxiv.org/abs/2504.11054
📍Hall 3 + Hall 2B #555
📅 Thu 24 Apr 10 AM — 12:30 PM
Don't forget to check out the demo for yourself: metamotivo.metademolab.com and the paper now on arXiv: arxiv.org/abs/2504.11054
Reposted by Jesse Farebrother
And for categorical representations, @brosa.ca openreview.net/forum?id=dVp... is pretty much canon at this point!
Stop Regressing: Training Value Functions via Classification for...
Value functions are an essential component in deep reinforcement learning (RL), that are typically trained via mean squared error regression to match bootstrapped target values. However, scaling...
openreview.net
January 31, 2025 at 6:16 AM
And for categorical representations, @brosa.ca openreview.net/forum?id=dVp... is pretty much canon at this point!
How can you 0-shot transfer predictions of long-term performance across reward functions *and* risk-sensitive utilities?
We can do this via Distributional Successor Features. Our recent work introduces the 1st tractable & provably convergent algos for learning DSFs.
#NeurIPS2024 #6704
12 Dec, 11-2
We can do this via Distributional Successor Features. Our recent work introduces the 1st tractable & provably convergent algos for learning DSFs.
#NeurIPS2024 #6704
12 Dec, 11-2
December 9, 2024 at 3:59 PM
we've used Atari games as an RL benchmark for so long, but for a little while it's bugged me that it's a discrete action problem, since the original joysticks were analog...
@jessefarebro.bsky.social & i fix this by introducing the Continuous ALE (CALE)!
read thread for details!
1/9
@jessefarebro.bsky.social & i fix this by introducing the Continuous ALE (CALE)!
read thread for details!
1/9
December 9, 2024 at 3:59 PM
This is how our work on classification vs. regression started, it was folk knowledge in many circles but I had overestimated the extent to which the wider community knew this. openreview.net/forum?id=dVp...
Stop Regressing: Training Value Functions via Classification for...
Value functions are an essential component in deep reinforcement learning (RL), that are typically trained via mean squared error regression to match bootstrapped target values. However, scaling...
openreview.net
November 27, 2024 at 1:39 PM
This is how our work on classification vs. regression started, it was folk knowledge in many circles but I had overestimated the extent to which the wider community knew this. openreview.net/forum?id=dVp...
Jax RL work as in writing envs in Jax? If so, each has their place, eg, look at Mujoco in envpool vs MJX, there’s a clear tradeoff point as you increase the number of environments.
November 24, 2024 at 10:21 AM
Jax RL work as in writing envs in Jax? If so, each has their place, eg, look at Mujoco in envpool vs MJX, there’s a clear tradeoff point as you increase the number of environments.
👋 can I be added as well?
November 24, 2024 at 9:44 AM
👋 can I be added as well?