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
Excited to be in Singapore 🇸🇬 for #ICLR25! We’ll present 1) Meta Motivo, a first-of-its-kind model enabling zero-shot humanoid control for any reward, goal, or motion; 2) imitation via successor feature matching; 3) flow matching for generative TD learning of future experience.
April 22, 2025 at 9:26 PM
Excited to be in Singapore 🇸🇬 for #ICLR25! We’ll present 1) Meta Motivo, a first-of-its-kind model enabling zero-shot humanoid control for any reward, goal, or motion; 2) imitation via successor feature matching; 3) flow matching for generative TD learning of future experience.
As an undergraduate student, taking Rich's course at @ualberta.bsky.social was a defining moment in my academic journey. His work and teachings have shaped the paths of countless researchers, including my own. Congrats, Rich & Andy!
Meet the recipients of the 2024 ACM A.M. Turing Award, Andrew G. Barto and Richard S. Sutton! They are recognized for developing the conceptual and algorithmic foundations of reinforcement learning. Please join us in congratulating the two recipients! bit.ly/4hpdsbD
March 5, 2025 at 5:43 PM
As an undergraduate student, taking Rich's course at @ualberta.bsky.social was a defining moment in my academic journey. His work and teachings have shaped the paths of countless researchers, including my own. Congrats, Rich & Andy!
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!
Reposted by Jesse Farebrother
This paper by @harwiltz.bsky.social and colleagues is one of the high points of #NeurIPS2024 for me so far:
arxiv.org/abs/2409.00328
arxiv.org/abs/2409.00328
Foundations of Multivariate Distributional Reinforcement Learning
In reinforcement learning (RL), the consideration of multivariate reward signals has led to fundamental advancements in multi-objective decision-making, transfer learning, and representation learning....
arxiv.org
December 12, 2024 at 9:40 PM
This paper by @harwiltz.bsky.social and colleagues is one of the high points of #NeurIPS2024 for me so far:
arxiv.org/abs/2409.00328
arxiv.org/abs/2409.00328
Reposted by Jesse Farebrother
Come by West Ballroom A-D #6404 4:30 PM–7:30 PM tonight (Thursday) to talk to @jessefarebro.bsky.social and me about CALE!
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 12, 2024 at 6:32 PM
Come by West Ballroom A-D #6404 4:30 PM–7:30 PM tonight (Thursday) to talk to @jessefarebro.bsky.social and me about CALE!
Landed in Vancouver for #NeurIPS. We’ll be presenting a couple of papers with @pcastr.bsky.social and @harwiltz.bsky.social 🧵👇 and stay tuned later in the week for an exciting announcement!
December 9, 2024 at 3:59 PM
Landed in Vancouver for #NeurIPS. We’ll be presenting a couple of papers with @pcastr.bsky.social and @harwiltz.bsky.social 🧵👇 and stay tuned later in the week for an exciting announcement!
Reposted by Jesse Farebrother
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 3:30 PM
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
Reposted by Jesse Farebrother
Distributional SFs: enable 0-shot generalization of return *distribution* functions across a finite-dimensional reward function class
"Foundations of Multivariate Distributional Reinforcement Learning"
#NeurIPS2024 #6704
12 Dec 11am-2pm
neurips.cc/virtual/2024...
Wiltzer Farebrother Rowland
"Foundations of Multivariate Distributional Reinforcement Learning"
#NeurIPS2024 #6704
12 Dec 11am-2pm
neurips.cc/virtual/2024...
Wiltzer Farebrother Rowland
December 8, 2024 at 10:43 PM
Distributional SFs: enable 0-shot generalization of return *distribution* functions across a finite-dimensional reward function class
"Foundations of Multivariate Distributional Reinforcement Learning"
#NeurIPS2024 #6704
12 Dec 11am-2pm
neurips.cc/virtual/2024...
Wiltzer Farebrother Rowland
"Foundations of Multivariate Distributional Reinforcement Learning"
#NeurIPS2024 #6704
12 Dec 11am-2pm
neurips.cc/virtual/2024...
Wiltzer Farebrother Rowland
Reposted by Jesse Farebrother
📢 In Defense Of Atari 📢
New blog post in which I argue why the ALE is still a valuable resource for RL research!
psc-g.github.io/posts/resear...
New blog post in which I argue why the ALE is still a valuable resource for RL research!
psc-g.github.io/posts/resear...
December 4, 2024 at 12:07 AM
📢 In Defense Of Atari 📢
New blog post in which I argue why the ALE is still a valuable resource for RL research!
psc-g.github.io/posts/resear...
New blog post in which I argue why the ALE is still a valuable resource for RL research!
psc-g.github.io/posts/resear...
Reposted by Jesse Farebrother
Come join us at Trinity College Dublin for the 6th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM2025)
Abstract deadline January 15: rldm.org/submit
Abstract deadline January 15: rldm.org/submit
November 15, 2024 at 10:53 AM
Come join us at Trinity College Dublin for the 6th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM2025)
Abstract deadline January 15: rldm.org/submit
Abstract deadline January 15: rldm.org/submit