Search Results for author:
Found 7 papers, 2 papers with code
Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
On the control side, we train a latent dynamics model using the Joint Embedding Predictive Architecture (JEPA) and use it for planning.
$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
Based on this observation, we revise the standard contrastive loss to explicitly encode how a sample relates to others.
Hierarchical World Models as Visual Whole-Body Humanoid Controllers
Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology.
Gradient-based Planning with World Models
The enduring challenge in the field of artificial intelligence has been the control of systems to achieve desired behaviours.
A Cookbook of Self-Supervised Learning
Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning.
Joint Embedding Predictive Architectures Focus on Slow Features
Many common methods for learning a world model for pixel-based environments use generative architectures trained with pixel-level reconstruction objectives.
Light-weight probing of unsupervised representations for Reinforcement Learning
Unsupervised visual representation learning offers the opportunity to leverage large corpora of unlabeled trajectories to form useful visual representations, which can benefit the training of reinforcement learning (RL) algorithms.
