MODIP fine-tunes diffusion policies offline-to-online by training a world model, running MPC with terminal state values inside it to create targets, and using policy-independent TD critics, yielding gains over BC on D4RL and RoboMimic tasks.
arXiv preprint arXiv:2502.12631 , year=
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
-
MODIP: Efficient Model-Based Optimization for Diffusion Policies
MODIP fine-tunes diffusion policies offline-to-online by training a world model, running MPC with terminal state values inside it to create targets, and using policy-independent TD critics, yielding gains over BC on D4RL and RoboMimic tasks.