# Demystifying Action Space Design for Robotic Manipulation Policies

arXiv: https://arxiv.org/abs/2602.23408 · HTML: https://mlsanity.com/paper/2602.23408/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 43 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 30 of 37)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025)
- [GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation](https://mlsanity.com/paper/2410.06158/) (2024)
- [Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models](https://mlsanity.com/paper/2502.19417/) (2025)
- [Any-point Trajectory Modeling for Policy Learning](https://mlsanity.com/paper/2401.00025/) (2023)
- [Video Language Planning](https://mlsanity.com/paper/2310.10625/) (2023)
- [Behavior Generation with Latent Actions](https://mlsanity.com/paper/2403.03181/) (2024)
- [Data Scaling Laws in Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2410.18647/) (2024)
- [ALOHA Unleashed: A Simple Recipe for Robot Dexterity](https://mlsanity.com/paper/2410.13126/) (2024)
- [Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation](https://mlsanity.com/paper/2408.11812/) (2024)
- [GR-3 Technical Report](https://mlsanity.com/paper/2507.15493/) (2025)
- [OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning](https://mlsanity.com/paper/2505.11917/) (2025)
- [PointVLA: Injecting the 3D World into Vision-Language-Action Models](https://mlsanity.com/paper/2503.07511/) (2025)
- [ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation](https://mlsanity.com/paper/2505.22159/) (2025)

## Built on by (most cited first, 9 of 9)

- [StarVLA-α: Reducing Complexity in Vision-Language-Action Systems](https://mlsanity.com/paper/2604.11757/) (2026)
- [Wall-OSS-0.5 Technical Report](https://mlsanity.com/paper/2605.30877/) (2026)
- [X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining](https://mlsanity.com/paper/2606.14752/) (2026)
- [ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow](https://mlsanity.com/paper/2607.27924/) (2026)
- [See like a Robot: Robot-Centric Pointmaps for VLA Models](https://mlsanity.com/paper/2607.11498/) (2026)
- [SPACE: Enabling Learning from Cross-Robot Data Toward Generalist Policies](https://mlsanity.com/paper/2606.24049/) (2026)
- [Making two action heads agree: coordination mechanisms and a runtime collapse certificate for flow-matching policies](https://mlsanity.com/paper/2608.15748/) (2026)
- [SeeQ: Training Generalist Value Functions for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2609.22085/) (2026)
- [The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models](https://mlsanity.com/paper/2609.27070/) (2026)

## Abstract (arXiv)

The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the optimization landscape of policy learning. While recent advances have focused heavily on scaling training data and model capacity, the choice of action space remains guided by ad-hoc heuristics or legacy designs, leading to an ambiguous understanding of robotic policy design philosophies. To address this ambiguity, we conducted a large-scale and systematic empirical study, confirming that the action space does have significant and complex impacts on robotic policy learning. We dissect the action design space along temporal and spatial axes, facilitating a structured analysis of how these choices govern both policy learnability and control stability. Based on 13,000+ real-world rollouts on a bimanual robot and evaluation on 500+ trained models over four scenarios, we examine the trade-offs between absolute vs. delta representations, and joint-space vs. task-space parameterizations. Our large-scale results suggest that properly designing the policy to predict delta actions consistently improves performance, while joint-space and task-space representations offer complementary strengths, favoring control stability and generalization, respectively.