Search Results for author:
Found 3 papers, 2 papers with code
Vid2Act: Activate Offline Videos for Visual RL
Pretraining RL models on offline video datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in tasks, dynamics, and behaviors across domains.
Model-Based Reinforcement Learning with Isolated Imaginations
On top of our previous work, we further consider the sparse dependencies between controllable and noncontrollable states, address the training collapse problem of state decoupling, and validate our approach in transfer learning setups.
Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models
First, by optimizing the inverse dynamics, we encourage the world model to learn controllable and noncontrollable sources of spatiotemporal changes on isolated state transition branches.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
