Chuning Zhu
YOU?
Author Swipe
View article: Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets Open
Imitation learning has emerged as a promising approach towards building generalist robots. However, scaling imitation learning for large robot foundation models remains challenging due to its reliance on high-quality expert demonstrations.…
View article: ASID: Active Exploration for System Identification in Robotic Manipulation
ASID: Active Exploration for System Identification in Robotic Manipulation Open
Model-free control strategies such as reinforcement learning have shown the ability to learn control strategies without requiring an accurate model or simulator of the world. While this is appealing due to the lack of modeling requirements…
View article: Distributional Successor Features Enable Zero-Shot Policy Optimization
Distributional Successor Features Enable Zero-Shot Policy Optimization Open
Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through…
View article: Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning Open
Off-policy dynamic programming (DP) techniques such as $Q$-learning have proven to be important in sequential decision-making problems. In the presence of function approximation, however, these techniques often diverge due to the absence o…
View article: RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability
RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability Open
Visual model-based RL methods typically encode image observations into low-dimensional representations in a manner that does not eliminate redundant information. This leaves them susceptible to spurious variations -- changes in task-irrele…
View article: Self-Supervised Reinforcement Learning that Transfers using Random Features
Self-Supervised Reinforcement Learning that Transfers using Random Features Open
Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across task…
View article: Model-Based Reinforcement Learning via Latent-Space Collocation
Model-Based Reinforcement Learning via Latent-Space Collocation Open
The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future acti…
View article: Model-Based Reinforcement Learning via Latent-Space Collocation
Model-Based Reinforcement Learning via Latent-Space Collocation Open
The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future acti…