End-to-end Dynamic Matching Network for Multi-view Multi-person 3d Pose Estimation

no code implementations • ECCV 2020 • Congzhentao Huang, Shuai Jiang, Yang Li, Ziyue Zhang, Jason Traish, Chen Deng, Sam Ferguson, Richard Yi Da Xu

To address this phenomenon, we propose a novel end-to-end training scheme that brings the three separate modules into a single model.

3D Generation 3D Human Pose Estimation +1

Regularize! Don't Mix: Multi-Agent Reinforcement Learning without Explicit Centralized Structures

no code implementations • 19 Sep 2021 • Chapman Siu, Jason Traish, Richard Yi Da Xu

We propose using regularization for Multi-Agent Reinforcement Learning rather than learning explicit cooperative structures called {\em Multi-Agent Regularized Q-learning} (MARQ).

Multi-agent Reinforcement Learning Q-Learning +2

Dual Behavior Regularized Reinforcement Learning

no code implementations • 19 Sep 2021 • Chapman Siu, Jason Traish, Richard Yi Da Xu

We demonstrate the flexibility of this approach and how it can be adapted to online contexts where the environment is available to collect experiences and a variety of other contexts.

counterfactual reinforcement-learning +1

Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning

no code implementations • 19 Sep 2021 • Chapman Siu, Jason Traish, Richard Yi Da Xu

This paper introduces Greedy UnMix (GUM) for cooperative multi-agent reinforcement learning (MARL).

Multi-agent Reinforcement Learning Q-Learning +2