Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking

• URL: http://arxiv.org/abs/2510.12392v1
• Date: Tue, 14 Oct 2025 11:16:34 GMT
• Title: Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
• Authors: Junhyuk So, Chiwoong Lee, Shinyoung Lee, Jungseul Ok, Eunhyeok Park,
• Abstract summary: Generative Behavior Cloning is a simple yet effective framework for robot learning.<n>We propose two novel techniques to enhance the consistency and reactivity of diffusion policies.<n>Our approach substantially improves GBC performance across a wide range of simulated and real-world robotic manipulation tasks.
• Score: 29.920087317401396
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative Behavior Cloning (GBC) is a simple yet effective framework for robot learning, particularly in multi-task settings. Recent GBC methods often employ diffusion policies with open-loop (OL) control, where actions are generated via a diffusion process and executed in multi-step chunks without replanning. While this approach has demonstrated strong success rates and generalization, its inherent stochasticity can result in erroneous action sampling, occasionally leading to unexpected task failures. Moreover, OL control suffers from delayed responses, which can degrade performance in noisy or dynamic environments. To address these limitations, we propose two novel techniques to enhance the consistency and reactivity of diffusion policies: (1) self-guidance, which improves action fidelity by leveraging past observations and implicitly promoting future-aware behavior; and (2) adaptive chunking, which selectively updates action sequences when the benefits of reactivity outweigh the need for temporal consistency. Extensive experiments show that our approach substantially improves GBC performance across a wide range of simulated and real-world robotic manipulation tasks. Our code is available at https://github.com/junhyukso/SGAC

Related papers

• Primary-Fine Decoupling for Action Generation in Robotic Imitation [91.2899765310853]
  Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning.<n>We propose Primary-Fine Decoupling for Action Generation (PF-DAG), a two-stage framework that decouples coarse action consistency from fine-grained variations.<n>PF-DAG outperforms state-of-the-art baselines across 56 tasks from Adroit, DexArt, and MetaWorld benchmarks.
  arXiv  Detail & Related papers  (2026-02-25T08:36:45Z)
• Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning [9.92274274871221]
  Diffusion Policy has dominated action generation due to its strong capabilities for modeling multi-modal action distributions.<n>We propose $underlinetextbfS$parse $underlinetextbfA$ction$underlinetextbfG$en for extremely sparse action generation.
  arXiv  Detail & Related papers  (2026-01-19T09:50:36Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Much Ado About Noising: Dispelling the Myths of Generative Robotic Control [26.71643888212995]
  We evaluate popular generative control policies (GCPs) on common behavior cloning benchmarks.<n>We find that GCPs do not owe their success to their ability to capture multi-modality or to express more complex observation-to-action mappings.<n>Our results suggest that the distribution-fitting component of GCPs is less salient than commonly believed.
  arXiv  Detail & Related papers  (2025-12-01T15:44:53Z)
• Self-Guided Action Diffusion [53.38661283705301]
  Self-guided action diffusion is a more efficient variant of bidirectional decoding tailored for diffusion-based policies.<n>Our method achieves up to 70% higher success rates than existing counterparts on challenging dynamic tasks.
  arXiv  Detail & Related papers  (2025-08-17T00:39:15Z)
• Offline Learning of Controllable Diverse Behaviors [19.0544729496907]
  Imitation Learning (IL) techniques aim to replicate human behaviors in specific tasks.<n>We propose a new method based on temporal consistency and controllability.<n>We compare our approach to state-of-the-art methods over a diverse set of tasks and environments.
  arXiv  Detail & Related papers  (2025-04-25T08:16:56Z)
• Generative Predictive Control: Flow Matching Policies for Dynamic and Difficult-to-Demonstrate Tasks [11.780987653813792]
  We introduce generative predictive control, a supervised learning framework for tasks with fast dynamics.<n>We show how trained flow-matching policies can be warm-started at inference time, maintaining temporal consistency and enabling high-frequency feedback.
  arXiv  Detail & Related papers  (2025-02-19T03:33:01Z)
• Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling [51.38330727868982]
  We show how action chunking impacts the divergence between a learner and a demonstrator.<n>We propose Bidirectional Decoding (BID), a test-time inference algorithm that bridges action chunking with closed-loop adaptation.<n>Our method boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)
• Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution [51.83951489847344]
  In robotics applications, smooth control signals are commonly preferred to reduce system wear and energy efficiency. In this work, we aim to bridge this performance gap by growing discrete action spaces from coarse to fine control resolution. Our work indicates that an adaptive control resolution in combination with value decomposition yields simple critic-only algorithms that yield surprisingly strong performance on continuous control tasks.
  arXiv  Detail & Related papers  (2024-04-05T17:58:37Z)
• Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning [68.16998247593209]
  offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. In this paper, we propose an adaptive scheme for action quantization. We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
  arXiv  Detail & Related papers  (2023-10-18T06:07:10Z)
• Discrete Action On-Policy Learning with Action-Value Critic [72.20609919995086]
  Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension. We construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques.
  arXiv  Detail & Related papers  (2020-02-10T04:23:09Z)

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.