Deep Reinforcement Learning

We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources. Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation. Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn. After that, we discuss RL applications, including games, robotics, natural language processing (NLP), computer vision, finance, business management, healthcare, education, energy, transportation, computer systems, and, science, engineering, and art. Finally we summarize briefly, discuss challenges and opportunities, and close with an epilogue.

@article{liDeepReinforcementLearning2018,
  archivePrefix = {arXiv},
  eprinttype = {arxiv},
  eprint = {1810.06339},
  primaryClass = {cs, stat},
  title = {Deep {{Reinforcement Learning}}},
  url = {http://arxiv.org/abs/1810.06339},
  abstract = {We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources. Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation. Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn. After that, we discuss RL applications, including games, robotics, natural language processing (NLP), computer vision, finance, business management, healthcare, education, energy, transportation, computer systems, and, science, engineering, and art. Finally we summarize briefly, discuss challenges and opportunities, and close with an epilogue.},
  urldate = {2019-01-16},
  date = {2018-10-15},
  keywords = {Statistics - Machine Learning,Computer Science - Machine Learning},
  author = {Li, Yuxi},
  file = {/home/dimitri/Nextcloud/Zotero/storage/IRDZMEMJ/Li - 2018 - Deep Reinforcement Learning.pdf;/home/dimitri/Nextcloud/Zotero/storage/V8PVQIUQ/1810.html}
}

Downloads: 0

{"_id":"SMMC76w7c2JiP7qqe","bibbaseid":"li-deepreinforcementlearning","authorIDs":[],"author_short":["Li, Y."],"bibdata":{"bibtype":"article","type":"article","archiveprefix":"arXiv","eprinttype":"arxiv","eprint":"1810.06339","primaryclass":"cs, stat","title":"Deep Reinforcement Learning","url":"http://arxiv.org/abs/1810.06339","abstract":"We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources. Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation. Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn. After that, we discuss RL applications, including games, robotics, natural language processing (NLP), computer vision, finance, business management, healthcare, education, energy, transportation, computer systems, and, science, engineering, and art. Finally we summarize briefly, discuss challenges and opportunities, and close with an epilogue.","urldate":"2019-01-16","date":"2018-10-15","keywords":"Statistics - Machine Learning,Computer Science - Machine Learning","author":[{"propositions":[],"lastnames":["Li"],"firstnames":["Yuxi"],"suffixes":[]}],"file":"/home/dimitri/Nextcloud/Zotero/storage/IRDZMEMJ/Li - 2018 - Deep Reinforcement Learning.pdf;/home/dimitri/Nextcloud/Zotero/storage/V8PVQIUQ/1810.html","bibtex":"@article{liDeepReinforcementLearning2018,\n archivePrefix = {arXiv},\n eprinttype = {arxiv},\n eprint = {1810.06339},\n primaryClass = {cs, stat},\n title = {Deep {{Reinforcement Learning}}},\n url = {http://arxiv.org/abs/1810.06339},\n abstract = {We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources. Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation. Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn. After that, we discuss RL applications, including games, robotics, natural language processing (NLP), computer vision, finance, business management, healthcare, education, energy, transportation, computer systems, and, science, engineering, and art. Finally we summarize briefly, discuss challenges and opportunities, and close with an epilogue.},\n urldate = {2019-01-16},\n date = {2018-10-15},\n keywords = {Statistics - Machine Learning,Computer Science - Machine Learning},\n author = {Li, Yuxi},\n file = {/home/dimitri/Nextcloud/Zotero/storage/IRDZMEMJ/Li - 2018 - Deep Reinforcement Learning.pdf;/home/dimitri/Nextcloud/Zotero/storage/V8PVQIUQ/1810.html}\n}\n\n","author_short":["Li, Y."],"key":"liDeepReinforcementLearning2018","id":"liDeepReinforcementLearning2018","bibbaseid":"li-deepreinforcementlearning","role":"author","urls":{"Paper":"http://arxiv.org/abs/1810.06339"},"keyword":["Statistics - Machine Learning","Computer Science - Machine Learning"],"downloads":0},"bibtype":"article","biburl":"https://raw.githubusercontent.com/dlozeve/newblog/master/bib/all.bib","creationDate":"2020-01-08T20:39:39.223Z","downloads":0,"keywords":["statistics - machine learning","computer science - machine learning"],"search_terms":["deep","reinforcement","learning","li"],"title":"Deep Reinforcement Learning","year":null,"dataSources":["3XqdvqRE7zuX4cm8m"]}