{"id":14613,"date":"2015-09-26T00:40:52","date_gmt":"2015-09-25T21:40:52","guid":{"rendered":"http:\/\/hgpu.org\/?p=14613"},"modified":"2015-09-26T00:40:52","modified_gmt":"2015-09-25T21:40:52","slug":"from-pixels-to-torques-policy-learning-using-deep-dynamical-convolutional-networks","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=14613","title":{"rendered":"From Pixels to Torques: Policy Learning using Deep Dynamical Convolutional Networks"},"content":{"rendered":"<p>Data-efficient learning in continuous state-action spaces using high-dimensional observations remains an elusive challenge in developing fully autonomous systems. An instance of this challenge is the pixels to torques problem, which identifies key elements of an autonomous agent: autonomous thinking and decision making using sensor measurements only, learning from mistakes, and applying past experiences to novel situations. In this research, we introduce a deep dynamical convolutional model, able to learn complex non-linear dynamics and do long-term predictions. Compared to state-of-the-art reinforcement learning methods for continuous state and action space problems, our approach is solid and efficient as it is model-based, is scalable to high-dimensional state spaces, learns quickly, and is a major step towards fully autonomous learning from pixels to torques.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Data-efficient learning in continuous state-action spaces using high-dimensional observations remains an elusive challenge in developing fully autonomous systems. An instance of this challenge is the pixels to torques problem, which identifies key elements of an autonomous agent: autonomous thinking and decision making using sensor measurements only, learning from mistakes, and applying past experiences to novel [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,89,3],"tags":[330,1782,14,1673,1820,1025,20,176,1543,390],"class_list":["post-14613","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-cnn","tag-computer-science","tag-cuda","tag-deep-learning","tag-lua","tag-machine-learning","tag-nvidia","tag-package","tag-tesla-k40","tag-thesis"],"views":2974,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/14613","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=14613"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/14613\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=14613"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=14613"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=14613"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}