Learning From Rewardfree Offline Data A Case For Planning With Latent Dynamics Models
2 mentions across 1 person
Visit ↗All mentions
“In this work, we systematically evaluate RL and control-based methods on a suite of navigation tasks...planning with a latent dynamics model proves to be a strong approach for handling suboptimal offline data and adapting to diverse environments.”
JEPA-Based Latent Planning Outperforms Model-Free RL on Suboptimal Offline Data ↗