Understanding Behavior Cloning with Action Quantization

• URL: http://arxiv.org/abs/2603.20538v1
• Date: Fri, 20 Mar 2026 22:22:43 GMT
• Title: Understanding Behavior Cloning with Action Quantization
• Abstract summary: We analyze how quantization error propagates along the horizon and interacts with statistical sample complexity.<n>We show that behavior cloning with quantized actions and log-loss achieves optimal sample complexity.<n>We also propose a model-based augmentation that provably improves the error bound without requiring policy smoothness.
• Score: 12.649414799403054
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Behavior cloning is a fundamental paradigm in machine learning, enabling policy learning from expert demonstrations across robotics, autonomous driving, and generative models. Autoregressive models like transformer have proven remarkably effective, from large language models (LLMs) to vision-language-action systems (VLAs). However, applying autoregressive models to continuous control requires discretizing actions through quantization, a practice widely adopted yet poorly understood theoretically. This paper provides theoretical foundations for this practice. We analyze how quantization error propagates along the horizon and interacts with statistical sample complexity. We show that behavior cloning with quantized actions and log-loss achieves optimal sample complexity, matching existing lower bounds, and incurs only polynomial horizon dependence on quantization error, provided the dynamics are stable and the policy satisfies a probabilistic smoothness condition. We further characterize when different quantization schemes satisfy or violate these requirements, and propose a model-based augmentation that provably improves the error bound without requiring policy smoothness. Finally, we establish fundamental limits that jointly capture the effects of quantization error and statistical complexity.

Related papers

• Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning [83.65494573724904]
  We develop a principled MOL framework for diffusion models with limited data.<n>We propose a two-stage training procedure that first fits lightweight specialist models from limited paired data.<n>We establish bounds generalization showing that the required number of paired samples only depends on the complexity of the specialist model classes.
  arXiv  Detail & Related papers  (2026-05-24T18:19:40Z)
• Conformalized Quantum DeepONet Ensembles for Scalable Operator Learning with Distribution-Free Uncertainty [7.889588152000197]
  Operator learning enables fast surrogate modeling of high-dimensional dynamical systems.<n>Existing approaches face two fundamental limitations: quadratic inference complexity and unreliable uncertainty quantification.<n>We propose Conformalized Quantum DeepONet Ensembles, a framework that addresses both challenges simultaneously.
  arXiv  Detail & Related papers  (2026-05-01T01:13:59Z)
• Quantization-Aware Collaborative Inference for Large Embodied AI Models [67.66340659245186]
  Large artificial intelligence models (LAIMs) are increasingly regarded as a core intelligence engine for embodied AI applications.<n>To address this issue, we investigate quantization-aware collaborative inference (co-inference) for embodied AI systems.
  arXiv  Detail & Related papers  (2026-02-13T16:08:19Z)
• An Empirical Study of World Model Quantization [34.94388089174202]
  We present a systematic empirical study of world model quantization using DINO-WM.<n>We conduct experiments on different visual planning tasks across a wide range of bit-widths, quantization granularities, and planning horizons up to 50 iterations.<n>Results show that quantization effects in world models extend beyond standard accuracy and bit-width trade-offs.
  arXiv  Detail & Related papers  (2026-02-02T13:54:03Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation [7.193483612237862]
  In this study, we analyze the impact of quantization on model merging through the lens of error barriers.<n>We propose a novel post-training quantization, HDRQ - Hessian and distant regularizing quantization, that is designed to consider model merging for multi-target domain adaptation.<n>Our approach ensures that the quantization process incurs minimal deviation from the source pre-trained model while flattening the loss surface to facilitate smooth model merging.
  arXiv  Detail & Related papers  (2025-05-29T17:00:56Z)
• A Model-Based Approach to Imitation Learning through Multi-Step Predictions [8.888213496593556]
  We present a novel model-based imitation learning framework inspired by model predictive control.<n>Our method outperforms traditional behavior cloning numerical benchmarks.<n>We provide theoretical guarantees on the sample complexity and error bounds of our method, offering insights into its convergence properties.
  arXiv  Detail & Related papers  (2025-04-18T02:19:30Z)
• Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error [25.387541996071093]
  Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control.<n>One approach to mitigate compounding error is to train multi-step predictors directly, rather than relying on autoregressive rollout of a single-step model.<n>We show that when the model class is well-specified and accurately captures the system dynamics, single-step models achieve lower prediction error.<n>On the other hand, when the model class is misspecified due to partial observability, direct multi-step predictors can significantly reduce bias and thus outperform single-step approaches.
  arXiv  Detail & Related papers  (2025-04-02T14:18:52Z)
• Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems [53.03951222945921]
  We analyze smoothed (perturbed) policies, adding controlled random perturbations to the direction used by the linear oracle.<n>Our main contribution is a generalization bound that decomposes the excess risk into perturbation bias, statistical estimation error, and optimization error.<n>We illustrate the scope of the results on applications such as vehicle scheduling, highlighting how smoothing enables both tractable training and controlled generalization.
  arXiv  Detail & Related papers  (2024-07-24T12:00:30Z)
• Distributionally Robust Model-based Reinforcement Learning with Large State Spaces [55.14361269378122]
  Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment. We study distributionally robust Markov decision processes with continuous state spaces under the widely used Kullback-Leibler, chi-square, and total variation uncertainty sets. We propose a model-based approach that utilizes Gaussian Processes and the maximum variance reduction algorithm to efficiently learn multi-output nominal transition dynamics.
  arXiv  Detail & Related papers  (2023-09-05T13:42:11Z)
• Flexible Model Aggregation for Quantile Regression [92.63075261170302]
  Quantile regression is a fundamental problem in statistical learning motivated by a need to quantify uncertainty in predictions. We investigate methods for aggregating any number of conditional quantile models. All of the models we consider in this paper can be fit using modern deep learning toolkits.
  arXiv  Detail & Related papers  (2021-02-26T23:21:16Z)
• Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
  empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
  arXiv  Detail & Related papers  (2020-06-11T09:58:01Z)

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.