Self-Improving Embodied Foundation Models

• URL: http://arxiv.org/abs/2509.15155v1
• Date: Thu, 18 Sep 2025 17:00:08 GMT
• Title: Self-Improving Embodied Foundation Models
• Authors: Seyed Kamyar Seyed Ghasemipour, Ayzaan Wahid, Jonathan Tompson, Pannag Sanketi, Igor Mordatch,
• Abstract summary: We propose a two-stage post-training approach for robotics.<n>The first stage, Supervised Fine-Tuning (SFT), fine-tunes pretrained foundation models using both: a) behavioral cloning, and b) steps-to-go prediction objectives.<n>In the second stage, Self-Improvement, steps-to-go prediction enables the extraction of a well-shaped reward function and a robust success detector.
• Score: 21.81624145902717
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models trained on web-scale data have revolutionized robotics, but their application to low-level control remains largely limited to behavioral cloning. Drawing inspiration from the success of the reinforcement learning stage in fine-tuning large language models, we propose a two-stage post-training approach for robotics. The first stage, Supervised Fine-Tuning (SFT), fine-tunes pretrained foundation models using both: a) behavioral cloning, and b) steps-to-go prediction objectives. In the second stage, Self-Improvement, steps-to-go prediction enables the extraction of a well-shaped reward function and a robust success detector, enabling a fleet of robots to autonomously practice downstream tasks with minimal human supervision. Through extensive experiments on real-world and simulated robot embodiments, our novel post-training recipe unveils significant results on Embodied Foundation Models. First, we demonstrate that the combination of SFT and Self-Improvement is significantly more sample-efficient than scaling imitation data collection for supervised learning, and that it leads to policies with significantly higher success rates. Further ablations highlight that the combination of web-scale pretraining and Self-Improvement is the key to this sample-efficiency. Next, we demonstrate that our proposed combination uniquely unlocks a capability that current methods cannot achieve: autonomously practicing and acquiring novel skills that generalize far beyond the behaviors observed in the imitation learning datasets used during training. These findings highlight the transformative potential of combining pretrained foundation models with online Self-Improvement to enable autonomous skill acquisition in robotics. Our project website can be found at https://self-improving-efms.github.io .

Related papers

• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• Action Flow Matching for Continual Robot Learning [54.10050120844738]
  Continual learning in robotics seeks systems that can constantly adapt to changing environments and tasks.<n>We introduce a generative framework leveraging flow matching for online robot dynamics model alignment.<n>We find that by transforming the actions themselves rather than exploring with a misaligned model, the robot collects informative data more efficiently.
  arXiv  Detail & Related papers  (2025-04-25T16:26:15Z)
• Sample Efficient Robot Learning in Supervised Effect Prediction Tasks [0.0]
  MUSEL (Model Uncertainty for Sample-Efficient Learning) is a novel AL framework tailored for regression tasks in robotics.<n>We show that MUSEL improves both learning accuracy and sample efficiency, validating its effectiveness in learning action effects selecting informative samples.
  arXiv  Detail & Related papers  (2024-12-03T09:48:28Z)
• Affordance-Guided Reinforcement Learning via Visual Prompting [51.361977466993345]
  Keypoint-based Affordance Guidance for Improvements (KAGI) is a method leveraging rewards shaped by vision-language models (VLMs) for autonomous RL.<n>On diverse real-world manipulation tasks specified by natural language descriptions, KAGI improves the sample efficiency of autonomous RL and enables successful task completion in 30K online fine-tuning steps.
  arXiv  Detail & Related papers  (2024-07-14T21:41:29Z)
• Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation [8.940998315746684]
  We propose a model-based reinforcement learning (RL) approach for robotic arm end-tasks. We employ Bayesian neural network models to represent, in a probabilistic way, both the belief and information encoded in the dynamic model during exploration. Our experiments show the advantages of our Bayesian model-based RL approach, with similar quality in the results than relevant alternatives.
  arXiv  Detail & Related papers  (2024-04-02T11:44:37Z)
• Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning [58.3994826169858]
  We introduce RoboFuME, a reset-free fine-tuning system for robotic reinforcement learning. Our insights are to utilize offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy. Our method can incorporate data from an existing robot dataset and improve on a target task within as little as 3 hours of autonomous real-world experience.
  arXiv  Detail & Related papers  (2023-10-23T17:50:08Z)
• Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning [54.636562516974884]
  In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. In this work, we propose MEDAL++, a novel design for self-improving robotic systems. The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
  arXiv  Detail & Related papers  (2023-03-02T18:51:38Z)
• Scalable Multi-Task Imitation Learning with Autonomous Improvement [159.9406205002599]
  We build an imitation learning system that can continuously improve through autonomous data collection. We leverage the robot's own trials as demonstrations for tasks other than the one that the robot actually attempted. In contrast to prior imitation learning approaches, our method can autonomously collect data with sparse supervision for continuous improvement.
  arXiv  Detail & Related papers  (2020-02-25T18:56:42Z)

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.