ICML2018强化学习tutorial:ImitationLearning-深度学习文档类资源-CSDN下载

ICML 2018强化学习tutorial: Imitation Learning

所需积分/C币：11 2018-07-29 10:10:31 29.41MB PDF
15

收藏
举报

In this tutorial, we aim to present to researchers and industry practitioners a broad overview of imitation learning techniques and recent applications. Imitation learning is a powerful and practical alternative to reinforcement learning for learning sequential decision-making policies. Also known as learning from demonstrations or apprenticeship learning, imitation learning has benefited from recent progress in core learning techniques, increased availability & fidelity of demonstration data, as well as the computational advancements brought on by deep learning. We expect this tutorial to be highly relevant for researchers & practitioners who have interests in reinforcement learning, structured prediction, planning and control. The ideal audience member should have familiarity with basic supervised learning concepts. No knowledge of reinforcement learning techniques will be assumed.
Ingredients of Imitation Learning 身三R Qdddd STEAM Demonstrations or demonstrator Environment/ simulator Policy class VS Loss Function earning algorithm Tutorial overview Part 1: Introduction and core algorithms Part 2 Extensions and applications Teaser results Speech Animation Overview of ML landscape Structured prediction and search Types of Imitation learning Im proving over expert Core algorithms of passive, interactive Filtering and sequence modeling earning and cost learning Multi-objective imitation learning Visual /few-shot imitation learning Domain adaptation imitation learning Multi-agent imitation learning Hierarchical imitation learning Multi-modal imitation learning Weaker feedback ALVINN Dean pomerleau et al. 1989-1999 https://www.youtube.com/watch?v=ilp4apdtbpe Helicopter Acrobatics Learning for Control from Multiple Demonstrations Adam Coates. Pieter abbeel, Andrew Na ICML 2008 An Application of Reinforcement Learning to Aerobatic Helicopter Flight Pieter Abbeel, Adam Coates, Morgan Quigley, Andrew Y Ng, NIPS 2006 om/w 0JL04 Inferring Human Intent Planning-based Prediction for Pedestrians Brian ziebart et al.ros 2009 ?v=hio A Deep Learning Approach for Generalized Speech Animation Sarah Taylor, Taehwan Kim, Yisong Yue et al., SIGGRAPH 2017 ?y=9 NotE ARSEN QUEEN Ghosting 1 (Sports Analytics) Blue: Defense Attack White: Learning Policies d 1 6 Data Driven Ghosting using Deep Imitation Learning English Premier League Match date: 04/05/2013 2012-2013 Hoang M. Le et al. SSAC 2017 https://www.youtube.com/watch?v=wi-wl2cioca One Shot Imitation Learning Duan et al. niPs 17 httos://www.youtube.com/watch?v=omzwklizzcm Human in VR

...展开详情

深度学习强化学习 Imitation

试读 127P ICML 2018强化学习tutorial: Imitation Learning