潜在行動による行動生成
Behavior Generation with Latent Actions
連続行動を階層的ベクトル量子化でトークン化し、マルチモーダルな行動生成・条件付き生成・部分観測を扱うVQ-BeTを提案。模擬操作・自動運転・ロボティクスなど7環境でBeTやDiffusion Policiesを上回り、推論速度も5倍高速化した。
著者: Seungjae Lee, Yibin Wang, Haritheja Etukuru, H. Jin Kim, Nur Muhammad Mahi Shafiullah, Lerrel Pinto
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Generative modeling of complex behaviors from labeled datasets has been a longstanding problem in decision making. Unlike language or image generation, decision making requires modeling actions - continuous-valued vectors that are multimodal in their distribution, potentially drawn from uncurated sources, where generation errors can compound in sequential prediction. A recent class of models called Behavior Transformers (BeT) addresses this by discretizing actions using k-means clustering to capture different modes. However, k-means struggles to scale for high-dimensional action spaces or long sequences, and lacks gradient information, and thus BeT suffers in modeling long-range actions. In this work, we present Vector-Quantized Behavior Transformer (VQ-BeT), a versatile model for behavior generation that handles multimodal action prediction, conditional generation, and partial observations. VQ-BeT augments BeT by tokenizing continuous actions with a hierarchical vector quantization module. Across seven environments including simulated manipulation, autonomous driving, and robotics, VQ-BeT improves on state-of-the-art models such as BeT and Diffusion Policies. Importantly, we demonstrate VQ-BeT's improved ability to capture behavior modes while accelerating inference speed 5x over Diffusion Policies. Videos and code can be found https://sjlee.cc/vq-bet
