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
Drawing 28 questions from an 84-question bank: how I score a deadly sins quiz
0dev.to
Count tokens before you call the LLM: tiktoken encodings, token budgets and chunking, with real numbers
0dev.to
![Quadruped Robot Software — Ch.10: Quadruped AI and Physical AI [KR]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Ffiibwtdu8wij6gnnuoyc.png)
Quadruped Robot Software — Ch.10: Quadruped AI and Physical AI [KR]
0dev.to
Signal #138: Java4Shell Hits AVX-512 JDKs; GPT-6.2 Astra and Sol Ship
0dev.to

Check Support Emails Before the LLM: Wolf Defender in Apache Camel
0dev.to

The Librarian, the Missing Book, and the AI with a Master Key. Sentinel IR MCP
0dev.to