PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning

• URL: http://arxiv.org/abs/2606.21139v1
• Date: Fri, 19 Jun 2026 06:24:05 GMT
• Title: PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning
• Abstract summary: Latent action pretraining learns representations of visual change from pairs of observations.<n>We introduce Polar Latent Actions with Radial structure (PoLAR), which imposes a radial-direction structure on latent actions.<n>PoLAR improves downstream policy performance in simulation and real-world robot experiments.
• Score: 7.207198416919797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Latent action pretraining learns representations of visual change from pairs of observations, but existing methods typically encode each transition as a single unstructured representation that entangles transition extent and transition mode. We introduce Polar Latent Actions with Radial structure (PoLAR), which imposes a radial-direction structure on latent actions, encouraging radius to encode transition extent and direction to retain transition mode. PoLAR uses temporal offset between two observations as a weak proxy for transition extent, encouraging latent action from observation pairs separated by larger temporal gaps to occupy larger radii. We instantiate this structure in hyperbolic space, whose expanding volume with radius offers a natural fit for more diverse transition modes at larger extents. Across in-task and large-scale pretraining settings, PoLAR improves downstream policy performance in simulation and real-world robot experiments, outperforming latent action baselines and strong pretrained VLAs. These results suggest that the geometry of the latent action space is an important design choice for transferring visual pretraining to downstream robot policy learning.

Related papers

• Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models [6.732084106610505]
  World Action Models (WAMs) augment robot policies by predicting how task-relevant scene states may evolve under interaction.<n>Latent transitions are commonly realized with Transformer-based predictors whose inductive structure is centered on token interaction rather than temporal evolution.<n>We introduce the Latent Evolution Operator Network (LEON), which models latent evolution in a learned observable space through context-modulated operator-based propagation and additive forcing.
  arXiv  Detail & Related papers  (2026-08-27T15:43:44Z)
• DLAM: Distributional Latent Actions with Temporal Constraints [25.743937994244902]
  We introduce DLAM, a distributional latent-action model that represents each transition as a diagonal Gaussian.<n>For downstream policy learning, we freeze the encoder and train a flow-matching policy to jointly generate mean transition sequences and robot actions.<n>On held-out transitions, DLAM learns more temporally consistent latent dynamics than existing latent-action baselines and achieves stronger direct and cumulative reconstruction on held-out videos.
  arXiv  Detail & Related papers  (2026-07-29T17:09:48Z)
• Latent Actions from Factorized Transition Effects under Agent Ambiguity [15.872376579590437]
  We introduce Observed Transition Factorization (OTF), which decomposes each transition into a sparse set of observed transition primitives.<n>We also propose OTF-LAM, which abstracts motion primitives into action-like latents within the standard inverse-forward dynamics framework, and OTF-LAM-Dino, a decoder-free variant that predicts future states in a frozen DINOv2 representation space.
  arXiv  Detail & Related papers  (2026-06-29T16:45:04Z)
• Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning [85.02566758103008]
  Group-Graph Policy Optimization (G2PO) is a novel group-based Reinforcement Learning algorithm tailored for multi-turn agentic tasks.<n>G2PO substantially outperforms state-of-the-art prompt-based and RL baselines, achieving remarkable success rate improvements of up to 22.2% over GRPO.
  arXiv  Detail & Related papers  (2026-06-22T08:12:47Z)
• Deriving Hyperparameter Scaling Laws via Modern Optimization Theory [55.63126290312615]
  We study modern first-order boundss for methods based on the Linear Minimization Oracle (LMO)<n>Treating bounds in recent literature as a proxy and minimizing them across different tuning regimes yields closed-form power-law schedules for learning rate, momentum, and batch size.<n>Our results draw particular attention to the interaction between momentum and batch-size scaling, suggesting that optimal performance may be achieved with several scaling strategies.
  arXiv  Detail & Related papers  (2026-03-16T22:21:27Z)
• Structural Action Transformer for 3D Dexterous Manipulation [80.07649565189035]
  Cross-embodiment skill transfer is a challenge for high-DoF robotic hands.<n>Existing methods, often relying on 2D observations and temporal-centric action representation, struggle to capture 3D spatial relations.<n>This paper proposes a new 3D dexterous manipulation policy that challenges this paradigm by introducing a structural-centric perspective.
  arXiv  Detail & Related papers  (2026-03-04T11:38:12Z)
• \ extsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation [50.027425808733994]
  textscNaVIDA is a unified VLN framework that couples policy learning with action-grounded visual dynamics and adaptive execution.<n>textscNaVIDA augments training with chunk-based inverse-dynamics supervision to learn causal relationship between visual changes and corresponding actions.<n>Experiments show that textscNaVIDA achieves superior navigation performance compared to state-of-the-art methods with fewer parameters.
  arXiv  Detail & Related papers  (2026-01-26T06:16:17Z)
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy [73.75271615101754]
  We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences.<n>Dita employs in-context conditioning -- enabling fine-grained alignment between denoised actions and raw visual tokens from historical observations.<n>Dita effectively integrates cross-embodiment datasets across diverse camera perspectives, observation scenes, tasks, and action spaces.
  arXiv  Detail & Related papers  (2025-03-25T15:19:56Z)
• Diffusion Transformer Policy [48.50988753948537]
  We propose a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, to model continuous end-effector actions.<n>By leveraging the scaling capability of transformers, the proposed approach can effectively model continuous end-effector actions across large diverse robot datasets.
  arXiv  Detail & Related papers  (2024-10-21T12:43:54Z)
• A Hierarchical Hybrid Learning Framework for Multi-agent Trajectory Prediction [4.181632607997678]
  We propose a hierarchical hybrid framework of deep learning (DL) and reinforcement learning (RL) for multi-agent trajectory prediction. In the DL stage, the traffic scene is divided into multiple intermediate-scale heterogenous graphs based on which Transformer-style GNNs are adopted to encode heterogenous interactions. In the RL stage, we divide the traffic scene into local sub-scenes utilizing the key future points predicted in the DL stage.
  arXiv  Detail & Related papers  (2023-03-22T02:47:42Z)
• Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution [98.67737684075587]
  Generalization in partially observed markov decision processes (POMDPs) is critical for successful applications of visual reinforcement learning (VRL) We propose the reward sequence distribution conditioned on the starting observation and the predefined subsequent action sequence (RSD-OA) Experiments demonstrate that our representation learning approach based on RSD-OA significantly improves the generalization performance on unseen environments.
  arXiv  Detail & Related papers  (2023-02-19T15:47:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.