ROMar 17

Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting

arXiv:2603.1654282.51 citationsh-index: 11
AI Analysis

This addresses the challenge of adapting robot policies to diverse and noisy real-world data, though it is an incremental improvement over existing post-training methods.

The paper tackled the problem of offline post-training for robot policies on heterogeneous datasets, where uniform training averages over conflicting or low-quality data, by proposing Posterior-Transition Reweighting (PTR) to reweight samples based on post-action consequence attribution, resulting in improved adaptation without requiring reward signals.

Offline post-training adapts a pretrained robot policy to a target dataset by supervised regression on recorded actions. In practice, robot datasets are heterogeneous: they mix embodiments, camera setups, and demonstrations of varying quality, so many trajectories reflect recovery behavior, inconsistent operator skill, or weakly informative supervision. Uniform post-training gives equal credit to all samples and can therefore average over conflicting or low-attribution data. We propose Posterior-Transition Reweighting (PTR), a reward-free and conservative post-training method that decides how much each training sample should influence the supervised update. For each sample, PTR encodes the observed post-action consequence as a latent target, inserts it into a candidate pool of mismatched targets, and uses a separate transition scorer to estimate a softmax identification posterior over target indices. The posterior-to-uniform ratio defines the PTR score, which is converted into a clipped-and-mixed weight and applied to the original action objective through self-normalized weighted regression. This construction requires no tractable policy likelihood and is compatible with both diffusion and flow-matching action heads. Rather than uniformly trusting all recorded supervision, PTR reallocates credit according to how attributable each sample's post-action consequence is under the current representation, improving conservative offline adaptation to heterogeneous robot data.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes