際際滷shows by User: ssuserbd7730 / http://www.slideshare.net/images/logo.gif 際際滷shows by User: ssuserbd7730 / Sat, 23 Feb 2019 13:15:09 GMT 際際滷Share feed for 際際滷shows by User: ssuserbd7730 螳糾骸 LV&A 蠏碁Μ螻 Navigation Agent /slideshow/lva-navigation-agent/133004465 rlkorealva-190223131509
AI(Language, Vision, Action) Agent]]>
AI(Language, Vision, Action) Agent]]> Sat, 23 Feb 2019 13:15:09 GMT /slideshow/lva-navigation-agent/133004465 ssuserbd7730@slideshare.net(ssuserbd7730) 螳糾骸 LV&A 蠏碁Μ螻 Navigation Agent ssuserbd7730 AI(Language, Vision, Action) Agent <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/rlkorealva-190223131509-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> AI(Language, Vision, Action) Agent
螳糾骸 LV&A 蠏碁Μ螻 Navigation Agent from Yechan(Paul) Kim
]]> 1229 1 https://cdn.slidesharecdn.com/ss_thumbnails/rlkorealva-190223131509-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Neural module Network /slideshow/neural-module-network/128927281 neuralmodulenetworkpaulkim-190123111310
Neural Module Network 襴觀]]>
Neural Module Network 襴觀]]> Wed, 23 Jan 2019 11:13:10 GMT /slideshow/neural-module-network/128927281 ssuserbd7730@slideshare.net(ssuserbd7730) Neural module Network ssuserbd7730 Neural Module Network 襴觀 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/neuralmodulenetworkpaulkim-190123111310-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Neural Module Network 襴觀
Neural module Network from Yechan(Paul) Kim
]]> 564 3 https://cdn.slidesharecdn.com/ss_thumbnails/neuralmodulenetworkpaulkim-190123111310-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks /slideshow/learning-to-communicate-to-solve-riddles-with-deep-distributed-recurrent-qnetworks-128910642/128910642 madrllearningtocommunicatetosolveriddleswithdeepdistributedrecurrentq-networks-190123071640
MADRL襦壱危 - Learning to Communicate to Solver Riddles with Deep Distributed Recurrent Q-Networks]]>
MADRL襦壱危 - Learning to Communicate to Solver Riddles with Deep Distributed Recurrent Q-Networks]]> Wed, 23 Jan 2019 07:16:40 GMT /slideshow/learning-to-communicate-to-solve-riddles-with-deep-distributed-recurrent-qnetworks-128910642/128910642 ssuserbd7730@slideshare.net(ssuserbd7730) Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks ssuserbd7730 MADRL襦壱危 - Learning to Communicate to Solver Riddles with Deep Distributed Recurrent Q-Networks <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/madrllearningtocommunicatetosolveriddleswithdeepdistributedrecurrentq-networks-190123071640-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> MADRL襦壱危 - Learning to Communicate to Solver Riddles with Deep Distributed Recurrent Q-Networks
Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks from Yechan(Paul) Kim
]]> 194 1 https://cdn.slidesharecdn.com/ss_thumbnails/madrllearningtocommunicatetosolveriddleswithdeepdistributedrecurrentq-networks-190123071640-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Multiagent Cooperative and Competition with Deep Reinforcement Learning /slideshow/multiagent-cooperative-and-competition-with-deep-reinforcement-learning/128908145 madrlmultiagentcooperativeandcompetitionwithdeepreinforcementlearning-190123063638
MADRL襦壱危 - Multiagent Cooperative and Competition with Deep Reinforcement Learning]]>
MADRL襦壱危 - Multiagent Cooperative and Competition with Deep Reinforcement Learning]]> Wed, 23 Jan 2019 06:36:38 GMT /slideshow/multiagent-cooperative-and-competition-with-deep-reinforcement-learning/128908145 ssuserbd7730@slideshare.net(ssuserbd7730) Multiagent Cooperative and Competition with Deep Reinforcement Learning ssuserbd7730 MADRL襦壱危 - Multiagent Cooperative and Competition with Deep Reinforcement Learning <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/madrlmultiagentcooperativeandcompetitionwithdeepreinforcementlearning-190123063638-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> MADRL襦壱危 - Multiagent Cooperative and Competition with Deep Reinforcement Learning
Multiagent Cooperative and Competition with Deep Reinforcement Learning from Yechan(Paul) Kim
]]> 631 2 https://cdn.slidesharecdn.com/ss_thumbnails/madrlmultiagentcooperativeandcompetitionwithdeepreinforcementlearning-190123063638-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 2018 global ai_bootcamp_seoul_HomeNavi(Reinforcement Learning, AI) /slideshow/2018-global-aibootcampseoulhomenavireinforcement-learning-ai/125946417 2018globalaibootcampseoulpaulkim-181215105758
2018 global AI bootcamp seoul : HomeNavi Home Navigation螻 蟯 覦襭. language螻 Vision 蠏碁Μ螻 RL Task襯 企企 蠍一 伎 願 殊危 襭 ]]>
2018 global AI bootcamp seoul : HomeNavi Home Navigation螻 蟯 覦襭. language螻 Vision 蠏碁Μ螻 RL Task襯 企企 蠍一 伎 願 殊危 襭 ]]> Sat, 15 Dec 2018 10:57:58 GMT /slideshow/2018-global-aibootcampseoulhomenavireinforcement-learning-ai/125946417 ssuserbd7730@slideshare.net(ssuserbd7730) 2018 global ai_bootcamp_seoul_HomeNavi(Reinforcement Learning, AI) ssuserbd7730 2018 global AI bootcamp seoul : HomeNavi Home Navigation螻 蟯 覦襭. language螻 Vision 蠏碁Μ螻 RL Task襯 企企 蠍一 伎 願 殊危 襭 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2018globalaibootcampseoulpaulkim-181215105758-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> 2018 global AI bootcamp seoul : HomeNavi Home Navigation螻 蟯 覦襭. language螻 Vision 蠏碁Μ螻 RL Task襯 企企 蠍一 伎 願 殊危 襭
2018 global ai_bootcamp_seoul_HomeNavi(Reinforcement Learning, AI) from Yechan(Paul) Kim
]]> 222 3 https://cdn.slidesharecdn.com/ss_thumbnails/2018globalaibootcampseoulpaulkim-181215105758-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 3D Environment : HomeNavigation /slideshow/3d-environment-homenavigation-119366483/119366483 homenavigation-181014083104
LV&A(Language, Vision and Action) 3D Environment : HomeNavigation - Env : VizDoom, House3D - Multi-Modal Fusion : Gated-CNN, Gated-LSTM - Reinforcement Learning : A3C, DDPG 蟾蠍磯 : https://github.com/kibeomKim 蟾谿 : https://github.com/suhoy901 燕蟆 : https://github.com/tegg89 : https://github.com/hongdam 伎 : https://github.com/wooridle]]>
LV&A(Language, Vision and Action) 3D Environment : HomeNavigation - Env : VizDoom, House3D - Multi-Modal Fusion : Gated-CNN, Gated-LSTM - Reinforcement Learning : A3C, DDPG 蟾蠍磯 : https://github.com/kibeomKim 蟾谿 : https://github.com/suhoy901 燕蟆 : https://github.com/tegg89 : https://github.com/hongdam 伎 : https://github.com/wooridle]]> Sun, 14 Oct 2018 08:31:04 GMT /slideshow/3d-environment-homenavigation-119366483/119366483 ssuserbd7730@slideshare.net(ssuserbd7730) 3D Environment : HomeNavigation ssuserbd7730 LV&A(Language, Vision and Action) 3D Environment : HomeNavigation - Env : VizDoom, House3D - Multi-Modal Fusion : Gated-CNN, Gated-LSTM - Reinforcement Learning : A3C, DDPG 蟾蠍磯 : https://github.com/kibeomKim 蟾谿 : https://github.com/suhoy901 燕蟆 : https://github.com/tegg89 : https://github.com/hongdam 伎 : https://github.com/wooridle <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/homenavigation-181014083104-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> LV&amp;A(Language, Vision and Action) 3D Environment : HomeNavigation - Env : VizDoom, House3D - Multi-Modal Fusion : Gated-CNN, Gated-LSTM - Reinforcement Learning : A3C, DDPG 蟾蠍磯 : https://github.com/kibeomKim 蟾谿 : https://github.com/suhoy901 燕蟆 : https://github.com/tegg89 : https://github.com/hongdam 伎 : https://github.com/wooridle
3D Environment : HomeNavigation from Yechan(Paul) Kim
]]> 155 2 https://cdn.slidesharecdn.com/ss_thumbnails/homenavigation-181014083104-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Diversity is all you need(DIAYN) : Learning Skills without a Reward Function /slideshow/diversity-is-all-you-needdiayn-learning-skills-without-a-reward-function/117168978 diversityisallyouneed-180928221251
Diversity is all you need(DIAYN) paper review]]>
Diversity is all you need(DIAYN) paper review]]> Fri, 28 Sep 2018 22:12:51 GMT /slideshow/diversity-is-all-you-needdiayn-learning-skills-without-a-reward-function/117168978 ssuserbd7730@slideshare.net(ssuserbd7730) Diversity is all you need(DIAYN) : Learning Skills without a Reward Function ssuserbd7730 Diversity is all you need(DIAYN) paper review <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/diversityisallyouneed-180928221251-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Diversity is all you need(DIAYN) paper review
Diversity is all you need(DIAYN) : Learning Skills without a Reward Function from Yechan(Paul) Kim
]]> 679 1 https://cdn.slidesharecdn.com/ss_thumbnails/diversityisallyouneed-180928221251-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 pyconkr 2018 RL_Adventure : Rainbow(value based Reinforcement Learning) /ssuserbd7730/pyconkr-2018-rladventure-rainbowvalue-based-reinforcement-learning-110269309 pycon-2018rladventurerainbow-180817131625
伎 貊襴 2018 襴 語 "RL Adventure : DQN 覿 Rainbow DQN蟾讌" 覦 襭. 4覯讌 語 Rainbow 蟯 伎 https://github.com/hongdam/pycon2018-RL_Adventure]]>
伎 貊襴 2018 襴 語 "RL Adventure : DQN 覿 Rainbow DQN蟾讌" 覦 襭. 4覯讌 語 Rainbow 蟯 伎 https://github.com/hongdam/pycon2018-RL_Adventure]]> Fri, 17 Aug 2018 13:16:25 GMT /ssuserbd7730/pyconkr-2018-rladventure-rainbowvalue-based-reinforcement-learning-110269309 ssuserbd7730@slideshare.net(ssuserbd7730) pyconkr 2018 RL_Adventure : Rainbow(value based Reinforcement Learning) ssuserbd7730 伎 貊襴 2018 襴 語 "RL Adventure : DQN 覿 Rainbow DQN蟾讌" 覦 襭. 4覯讌 語 Rainbow 蟯 伎 https://github.com/hongdam/pycon2018-RL_Adventure <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/pycon-2018rladventurerainbow-180817131625-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> 伎 貊襴 2018 襴 語 &quot;RL Adventure : DQN 覿 Rainbow DQN蟾讌&quot; 覦 襭. 4覯讌 語 Rainbow 蟯 伎 https://github.com/hongdam/pycon2018-RL_Adventure
pyconkr 2018 RL_Adventure : Rainbow(value based Reinforcement Learning) from Yechan(Paul) Kim
]]> 244 4 https://cdn.slidesharecdn.com/ss_thumbnails/pycon-2018rladventurerainbow-180817131625-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 pycon2018 "RL Adventure : DQN 覿 Rainbow DQN蟾讌" /slideshow/pyconkr-2018-rladventureto-the-rainbow/110260030 pyconkr2018rladventure-180817113545
伎 貊襴 2018 襴 語 "RL Adventure : DQN 覿 Rainbow DQN蟾讌" 覦 襭. 2017 Deepmind 覦 value based 螳 覈 Rainbow 危企ゼ 蠍 襴朱 DQN覿 Rainbow蟾讌 谿朱 譴 襷 暑 伎 れ伎給. 1 : DQN, Double & Dueling DQN - 燕蟆 2 : PER and NoisyNet - 3 : Distributed RL - 伎 4 : RAINBOW - 蟾谿 蟯 貊 蟲豌企ゼ 誤螻 苦殊 覿れ https://github.com/hongdam/pycon2018-RL_Adventure 誤 給]]>
伎 貊襴 2018 襴 語 "RL Adventure : DQN 覿 Rainbow DQN蟾讌" 覦 襭. 2017 Deepmind 覦 value based 螳 覈 Rainbow 危企ゼ 蠍 襴朱 DQN覿 Rainbow蟾讌 谿朱 譴 襷 暑 伎 れ伎給. 1 : DQN, Double & Dueling DQN - 燕蟆 2 : PER and NoisyNet - 3 : Distributed RL - 伎 4 : RAINBOW - 蟾谿 蟯 貊 蟲豌企ゼ 誤螻 苦殊 覿れ https://github.com/hongdam/pycon2018-RL_Adventure 誤 給]]> Fri, 17 Aug 2018 11:35:45 GMT /slideshow/pyconkr-2018-rladventureto-the-rainbow/110260030 ssuserbd7730@slideshare.net(ssuserbd7730) pycon2018 "RL Adventure : DQN 覿 Rainbow DQN蟾讌" ssuserbd7730 伎 貊襴 2018 襴 語 "RL Adventure : DQN 覿 Rainbow DQN蟾讌" 覦 襭. 2017 Deepmind 覦 value based 螳 覈 Rainbow 危企ゼ 蠍 襴朱 DQN覿 Rainbow蟾讌 谿朱 譴 襷 暑 伎 れ伎給. 1 : DQN, Double & Dueling DQN - 燕蟆 2 : PER and NoisyNet - 3 : Distributed RL - 伎 4 : RAINBOW - 蟾谿 蟯 貊 蟲豌企ゼ 誤螻 苦殊 覿れ https://github.com/hongdam/pycon2018-RL_Adventure 誤 給 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/pyconkr2018rladventure-180817113545-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> 伎 貊襴 2018 襴 語 &quot;RL Adventure : DQN 覿 Rainbow DQN蟾讌&quot; 覦 襭. 2017 Deepmind 覦 value based 螳 覈 Rainbow 危企ゼ 蠍 襴朱 DQN覿 Rainbow蟾讌 谿朱 譴 襷 暑 伎 れ伎給. 1 : DQN, Double &amp; Dueling DQN - 燕蟆 2 : PER and NoisyNet - 3 : Distributed RL - 伎 4 : RAINBOW - 蟾谿 蟯 貊 蟲豌企ゼ 誤螻 苦殊 覿れ https://github.com/hongdam/pycon2018-RL_Adventure 誤 給
pycon2018 "RL Adventure : DQN 覿 Rainbow DQN蟾讌" from Yechan(Paul) Kim
]]> 2127 3 https://cdn.slidesharecdn.com/ss_thumbnails/pyconkr2018rladventure-180817113545-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-ssuserbd7730-48x48.jpg?cb=1727169754 RL awesome github.com/suhoy901 https://cdn.slidesharecdn.com/ss_thumbnails/rlkorealva-190223131509-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/lva-navigation-agent/133004465 螳糾骸 LV&amp;A 蠏碁Μ螻 Navigat... https://cdn.slidesharecdn.com/ss_thumbnails/neuralmodulenetworkpaulkim-190123111310-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/neural-module-network/128927281 Neural module Network https://cdn.slidesharecdn.com/ss_thumbnails/madrllearningtocommunicatetosolveriddleswithdeepdistributedrecurrentq-networks-190123071640-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/learning-to-communicate-to-solve-riddles-with-deep-distributed-recurrent-qnetworks-128910642/128910642 Learning to Communicat...