# VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning

arXiv: https://arxiv.org/abs/2509.25718 · HTML: https://mlsanity.com/paper/2509.25718/

## Key facts

- Cited by 4 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 14 of its 16 references that are in the map.
- First posted on arXiv 30 Sep 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, 14 of 14)

- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy](https://mlsanity.com/paper/2502.05450/) (2025)
- [FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning](https://mlsanity.com/paper/2409.16578/) (2024)
- [Affordance-Guided Reinforcement Learning via Visual Prompting](https://mlsanity.com/paper/2407.10341/) (2024)
- [Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends](https://mlsanity.com/paper/2506.20966/) (2025)
- [LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers](https://mlsanity.com/paper/2312.08958/) (2023)

## Built on by (most cited first, 4 of 4)

- [CounterAlign: Counterfactual Supervision for Vision-Language-Action Models](https://mlsanity.com/paper/2608.21740/) (2026)
- [SmoothRL: Online Reinforcement Learning During Asynchronous Execution](https://mlsanity.com/paper/2608.29768/) (2026)
- [Demonstration-Free Success-Probability Reward Learning for Generalist Robot Policies](https://mlsanity.com/paper/2609.33653/) (2026)
- [Action Chunking Proximal Policy Optimization with Feedback Correction](https://mlsanity.com/paper/2609.36250/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) is a promising avenue for post-training vision-language-action (VLA) models, but practical deployment is hindered by sparse rewards and unstable training. This work mitigates these challenges by introducing an action chunk based on proximal policy optimization (PPO) with behavior cloning using self-collected demonstrations. Aggregating consecutive actions into chunks improves the temporal consistency of the policy and the density of informative feedback. In addition, an auxiliary behavior cloning loss is applied with a dynamically updated demonstration buffer that continually collects high-quality task trials during training. The relative weight between the action-chunked PPO objective and the self behavior clone auxiliary loss is adapted online to stabilize the post-training process. Experiments on the MetaWorld benchmark indicate improved performance over supervised fine-tuning, achieving a high success rate (0.93) and few steps to success (42.17). These results demonstrate the viability of RL for VLA post-training and help lay the groundwork for downstream VLA applications.