Quantization-Free Autoregressive Action Transformer
Current transformer-based imitation learning approaches introduce discrete action representations and train an autoregressive transformer decoder on the resulting latent code. However, the initial quantization breaks the continuous structure of the action space thereby limiting the capabilities of the generative model. We propose a quantization-free method instead that leverages Generative Infinite-Vocabulary Transformers (GIVT) as a direct, continuous policy parametrization for autoregressive transformers. This simplifies the imitation learning pipeline while achieving state-of-the-art performance on a variety of popular simulated robotics tasks. We enhance our policy roll-outs by carefully studying sampling algorithms, further improving the results.
Code (1)
Tasks
Imitation LearningQuantizationSequential Decision MakingSimilar Papers 제목 키워드 기반
Understanding Behavior Cloning with Action Quantization
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 …
Continuous ControlAutonomous DrivingHiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matching
Coarse-to-fine autoregressive modeling has recently shown strong promise for visuomotor policy learning, combining the inference efficiency of autoregressive methods with the global trajectory coherence of diffusion-base…
Image GenerationTowards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization
Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned cod…
Image GenerationPositionQuantizationAutoregressive Image Generation using Residual Quantization
For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational c…
Conditional Image GenerationImage GenerationImage ReconstructionQuantization+1Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
Flow models have recently made great progress at modeling ordinal discrete data such as images and audio. Due to the continuous nature of flow models, dequantization is typically applied when using them for such discrete…