# TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization

arXiv: https://arxiv.org/abs/2506.08440 · HTML: https://mlsanity.com/paper/2506.08440/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)

## Builds on (most cited first, 30 of 42)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [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)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)

## Built on by (most cited first, 30 of 49)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025)
- [SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning](https://mlsanity.com/paper/2509.09674/) (2025)
- [Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2508.13073/) (2025)
- [VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators](https://mlsanity.com/paper/2510.00406/) (2025)
- [UI-Venus-1.5 Technical Report](https://mlsanity.com/paper/2602.09082/) (2026)
- [Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation](https://mlsanity.com/paper/2512.23703/) (2025)
- [RISE: Self-Improving Robot Policy with Compositional World Model](https://mlsanity.com/paper/2602.11075/) (2026)
- [SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models](https://mlsanity.com/paper/2511.15605/) (2025)
- [RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models](https://mlsanity.com/paper/2511.01331/) (2025)
- [Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends](https://mlsanity.com/paper/2506.20966/) (2025)
- [On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning](https://mlsanity.com/paper/2601.06748/) (2026)
- [Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2602.10503/) (2026)
- [chi0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies](https://mlsanity.com/paper/2602.09021/) (2026)
- [VLANeXt: Recipes for Building Strong VLA Models](https://mlsanity.com/paper/2602.18532/) (2026)
- [PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence](https://mlsanity.com/paper/2512.16793/) (2025)
- [DEAS: DEtached value learning with Action Sequence for Scalable Offline RL](https://mlsanity.com/paper/2510.07730/) (2025)
- [RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization](https://mlsanity.com/paper/2603.12639/) (2026)
- [ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation](https://mlsanity.com/paper/2603.27670/) (2026)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning](https://mlsanity.com/paper/2604.28192/) (2026)
- [Survey of Vision-Language-Action Models for Embodied Manipulation](https://mlsanity.com/paper/2508.15201/) (2025)
- [PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization](https://mlsanity.com/paper/2601.07182/) (2026)
- [TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation](https://mlsanity.com/paper/2602.09023/) (2026)
- [OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies](https://mlsanity.com/paper/2603.10052/) (2026)
- [HarnessPAI: An Evolving Harness for Physical AI](https://mlsanity.com/paper/2609.29166/) (2026)
- [E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes](https://mlsanity.com/paper/2604.04834/) (2026)
- [Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories](https://mlsanity.com/paper/2511.19528/) (2025)
- [Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time Intervention](https://mlsanity.com/paper/2511.22555/) (2025)
- [DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization](https://mlsanity.com/paper/2605.17486/) (2026)

## Abstract (arXiv)

Visual-Language-Action (VLA) models have demonstrated strong cross-scenario generalization capabilities in various robotic tasks through large-scale pre-training and task-specific fine-tuning. However, their training paradigm mainly relies on manually collected successful demonstrations, making it difficult to adapt to complex environments when encountering out-of-distribution (OOD) scenarios or execution biases. While Reinforcement Learning (RL) provides a closed-loop optimization framework via active trial-and-error mechanism, it suffers from sparse rewards, high variance, and unstable optimization in long-horizon robotic tasks. To address these limitations, we propose Trajectory-based Group Relative Policy Optimization (TGRPO), an online RL-based training framework for VLA models. TGRPO leverages task analysis generated by a large language model to automatically construct dense reward functions, providing fine-grained feedback to accelerate convergence and improve credit assignment. The core of our method is a group-based strategy that samples and normalizes multiple trajectories in parallel, reducing variance through relative comparison. By integrating trajectory-level and step-level advantage estimation, TGRPO captures both global and local optimization signals without relying on a value network. Experiments on four task categories of the LIBERO benchmark demonstrate that TGRPO achieves an average success rate of 80.7%, which is 4.2% higher than that of Supervised Fine-Tuning (SFT) and outperforms other representative RL-based post-training methods.