SMWM trains end-to-end latent world models from offline reward-free data using inverse dynamics regularization to prevent collapse and align states with controllable actions for planning.
Agent-controller representations: Principled offline RL with rich exogenous information.arXiv preprint arXiv:2211.00164, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sensorimotor World Models: Perception for Action via Inverse Dynamics
SMWM trains end-to-end latent world models from offline reward-free data using inverse dynamics regularization to prevent collapse and align states with controllable actions for planning.