Backend
Latent Action Policies from Suboptimal Data
arXiv stat.ML0 views
arXiv:2611.24482v1 Announce Type: cross Abstract: Latent Action Models (LAMs) learn control representations from action-free video, but existing pipelines typically train latent policies with behavioral cloning, without an explicit policy improvement objective. Although offline RL offers a natural approach to policy improvement, standard methods do not transfer directly to learned latent action spaces. We find that the structure of learned latent actions makes naive offline RL unreliable: directly maximizing value over latent actions or fitting a unimodal policy can produce latent actions that cannot be realized by physical execution, while the latent representation can merge physical controls that receive different rewards. To understand when latent-space optimization remains valid, we derive conditions under which policy improvement transfers to decoded execution and under which latent and physical optima align. Building on these insights, we propose LAPIS for goal-conditioned latent policy improvement, grounding value-based policy improvement in observed state-latent transitions and using a conditional flow policy to capture their multimodal structure. LAPIS outperforms baselines on most tasks, with the clearest gains in visual manipulation, and remains effective even with only 1% action labels, where competing methods largely collapse.
Source:https://arxiv.org/abs/2611.24482PreviousExtracting Training Data from Diffusion Language Models via InfillingNextThe geometry of neural network decision boundaries
Related posts
Supabase vs Neon vs PlanetScale: Serverless Database Branching, Latency & True TCO
0dev.to

Ping64|That One Windows XP Box Running the Production Line and the Fence We Built Around It
0dev.to
You Have Spotted a Mistake in the Figures Your Manager Is Presenting Tomorrow
0dev.to
My Tank Bot Kept Winning Fights and Losing Games — 10 Versions of Debugging battle.training
0dev.to

Ping64|Where Does the Attendance Machine Actually Store Everyone’s Fingerprint Templates, and Who Can Read Them
0dev.to
Split ratio is the least interesting spec on a power divider
0dev.to