Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations

no code implementations • 18 Dec 2023 • Zilin Wang, Haolin Zhuang, Lu Li, Yinmin Zhang, Junjie Zhong, Jun Chen, Yu Yang, Boshi Tang, Zhiyong Wu

This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models.

A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning

1 code implementation • 12 Dec 2023 • Yinmin Zhang, Jie Liu, Chuming Li, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

In this paper, from a novel perspective, we systematically study the challenges that remain in O2O RL and identify that the reason behind the slow improvement of the performance and the instability of online finetuning lies in the inaccurate Q-value estimation inherited from offline pretraining.

Offline RL

MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning

no code implementations • 18 Oct 2023 • Jie Liu, Yinmin Zhang, Chuming Li, Chao Yang, Yaodong Yang, Yu Liu, Wanli Ouyang

Building a single generalist agent with strong zero-shot capability has recently sparked significant advancements.

Decision Making SMAC+

Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection

no code implementations • ICCV 2023 • Xinzhu Ma, Yongtao Wang, Yinmin Zhang, Zhiyi Xia, Yuan Meng, Zhihui Wang, Haojie Li, Wanli Ouyang

In this work, we build a modular-designed codebase, formulate strong training recipes, design an error diagnosis toolbox, and discuss current methods for image-based 3D object detection.

3D Object Detection Object +1

Theoretically Guaranteed Policy Improvement Distilled from Model-Based Planning

no code implementations • 24 Jul 2023 • Chuming Li, Ruonan Jia, Jie Liu, Yinmin Zhang, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

Model-based reinforcement learning (RL) has demonstrated remarkable successes on a range of continuous control tasks due to its high sample efficiency.

Continuous Control Model-based Reinforcement Learning +1

ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency

1 code implementation • 29 Nov 2022 • Chuming Li, Jie Liu, Yinmin Zhang, Yuhong Wei, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action.

Decision Making Q-Learning +2

An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection

no code implementations • 15 Aug 2022 • Xinzhu Ma, Yuan Meng, Yinmin Zhang, Lei Bai, Jun Hou, Shuai Yi, Wanli Ouyang

We hope this work can provide insights for the image-based 3D detection community under a semi-supervised setting.

3D Object Detection Autonomous Driving +1

Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection

1 code implementation • 29 Jul 2021 • Yinmin Zhang, Xinzhu Ma, Shuai Yi, Jun Hou, Zhihui Wang, Wanli Ouyang, Dan Xu

In this paper, we propose to learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection.

Autonomous Driving Depth Estimation +4

Delving into Localization Errors for Monocular 3D Object Detection

1 code implementation • CVPR 2021 • Xinzhu Ma, Yinmin Zhang, Dan Xu, Dongzhan Zhou, Shuai Yi, Haojie Li, Wanli Ouyang

Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging.

3D Object Detection From Monocular Images Autonomous Driving +3