AI & ML
Grana: Compositional Reward Modeling for Long-Horizon Robot Manipulation
arXiv cs.RO0 views
arXiv:2611.24926v1 Announce Type: new Abstract: Robot reward modeling faces two challenges: generalizing across tasks and accurately tracking progress in long-horizon manipulation. General-purpose reward models demonstrate broad task transfer, but transfer from short-task pretraining to long-horizon tasks remains underexplored. Long-horizon progress models often rely on task-specific subtask classifiers or fixed action vocabularies, limiting the reuse of learned progress knowledge when adapting to new tasks. To address these challenges, we introduce Grana, a vision-language robot reward model that learns to identify unfinished subtasks and estimate their continuous progress using open-vocabulary subtask descriptions. We train a language-conditioned model to estimate progress in short-horizon tasks and individual subtasks of long-horizon tasks. For long-horizon tasks, we combine the selected subtask's predicted progress with credit for preceding completed subtasks to estimate whole-task progress. General progress prediction requires training the model across diverse tasks with progress supervision that accounts for imperfect execution. Elapsed-time proxies can misrepresent progress when relative subtask durations vary, or failures reverse local progress. We therefore introduce an annotation protocol that converts sparse subtask boundaries and action-quality annotations into dense progress targets, without requiring annotators to assign numerical progress scores. Pretraining with this supervision on 200 diverse, mostly short-horizon manipulation tasks enables zero-shot reward prediction on unseen tasks and improves progress prediction after adaptation to multi-minute, long-horizon tasks. Experiments demonstrate (i) generalizable reward prediction, including adaptation to five long-horizon tasks, (ii) benefits from pretraining and composing subtask progress estimates, and (iii) improved downstream policy performance.
Source:https://arxiv.org/abs/2611.24926PreviousRender the Robot, Generate the World: One Video World Model Across EmbodimentsNextPhoenix: Learning Scene Structure Representations for Generalizable World-Action Models
Related posts

How to Interpret Logistic Regression and Odds Ratios
0dev.to
Kubernetes Service Account Tokens Do Not Need to Ride Along
0dev.to Kubernetes
Export a calendar day to ICS for your system calendar
0dev.to OpenSource
Comparing Axleta Repository Packer with Gitingest
0dev.to Programming

Animating and rigging by hand is sometimes hard....
0dev.to Programming
Anthropic is bullshitting you about subagents and loops.
0dev.to Programming