activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Scalable Option Learning in High-Throughput Environments

Mikael Henaff, Scott Fujimoto, Michael Matthews +1

Hierarchical reinforcement learning (RL) has the potential to enable effective decision-making over long timescales. Existing approaches, while promising, have yet to realize the b…

cs.LG2026

Parallel Stochastic Gradient-Based Planning for World Models

Michael Psenka, Michael Rabbat, Aditi Krishnapriyan +2

World models simulate environment dynamics from raw sensory inputs like video. However, using them for planning can be challenging due to the vast and unstructured search space. We…

cs.LG2025

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density

Randall Balestriero, Nicolas Ballas, Mike Rabbat +1

Joint Embedding Predictive Architectures (JEPAs) learn representations able to solve numerous downstream tasks out-of-the-box. JEPAs combine two objectives: (i) a latent-space pred…

cs.LG2025

Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition

Priya Kasimbeg, Frank Schneider, Runa Eschenhagen +11

The goal of the AlgoPerf: Training Algorithms competition is to evaluate practical speed-ups in neural network training achieved solely by improving the underlying training algorit…

cs.LG2025

Towards General-Purpose Model-Free Reinforcement Learning

Scott Fujimoto, Pierluca D'Oro, Amy Zhang +2

Reinforcement learning (RL) promises a framework for near-universal problem-solving. In practice however, RL algorithms are often tailored to specific benchmarks, relying on carefu…