{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T11:07:43Z","timestamp":1781089663327,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8460655","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"5129-5136","source":"Crossref","is-referenced-by-count":201,"title":["Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation"],"prefix":"10.1109","author":[{"given":"Gregory","family":"Kahn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Villaflor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bosen","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","article-title":"A Distributional Perspective on Reinforcement Learning","author":"bellemare","year":"2017","journal-title":"ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2004.180"},{"key":"ref30","author":"deng","year":"2006","journal-title":"The Cross-Entropy Method A Unified Approach to Combinatorial Optimization Monte-Carlo Simulation and Machine Learning"},{"key":"ref10","article-title":"Application of intelligent automata to reconnaissance","author":"rosen","year":"1968","journal-title":"Tech Rep"},{"key":"ref11","author":"thrun","year":"2008","journal-title":"Probabilistic Robotics"},{"key":"ref12","first-page":"1442","author":"leonard","year":"1991","journal-title":"Simultaneous map building and localization for an autonomous mobile robot"},{"key":"ref13","article-title":"Find your own way: Weakly-supervised segmentation of path proposals for urban autonomy","author":"barnes","year":"2017","journal-title":"ICRA"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20276"},{"key":"ref15","article-title":"Safe Visual Navigation via Deep Learning and Novelty Detection","author":"richter","year":"2017","journal-title":"RSS"},{"key":"ref16","article-title":"Deepdriving: Learning affordance for direct perception in autonomous driving","author":"chen","year":"2015","journal-title":"ICCV"},{"key":"ref17","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"NIPS"},{"key":"ref18","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102426"},{"key":"ref28","article-title":"Action-conditional video prediction using deep networks in atari games","author":"oh","year":"2015","journal-title":"NIPS"},{"key":"ref4","author":"olson","year":"2008","journal-title":"Robust and Efficient Robotic Mapping"},{"key":"ref27","article-title":"Issues in Using Function Approximation for Reinforcement Learning","author":"thrun","year":"1993","journal-title":"Proceedings of the Fourth Connectionist Models Summer School"},{"key":"ref3","article-title":"Autonomous multi-floor indoor navigation with a computationally constrained MAV","author":"shen","year":"2011","journal-title":"ICRA"},{"key":"ref6","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013","journal-title":"NIPS *2010 Workshop on Deep Learning"},{"key":"ref29","article-title":"On multiplicative integration with recurrent neural networks","author":"wu","year":"2016","journal-title":"NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9365-8"},{"key":"ref8","article-title":"A Model-Based and Data-Efficient Approach to Policy Search","author":"deisenroth","year":"2011","journal-title":"ICML"},{"key":"ref7","article-title":"Continuous Control with Deep Reinforcement Learning","author":"lillicrap","year":"2016","journal-title":"ICRL"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref9","article-title":"Toward fast policy search for learning legged locomotion","author":"deisenroth","year":"2012","journal-title":"IROS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/34.3900"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2017.XIII.034","article-title":"(CAD)2 RL: Real Single-Image Flight without a Single Real Image","author":"sadeghi","year":"2017","journal-title":"RSS"},{"key":"ref22","article-title":"Multi-task learning with deep model based reinforcement learning","author":"mujika","year":"2016"},{"key":"ref21","article-title":"Dyna, an Integrated Architecture for Learning, Planning, and Reacting","author":"sutton","year":"0","journal-title":"AAAI 1991"},{"key":"ref24","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"kahn","year":"2017"},{"key":"ref23","article-title":"Value Prediction Network","author":"oh","year":"2017","journal-title":"NIPS"},{"key":"ref26","author":"gupta","year":"2017","journal-title":"Cognitive mapping and planning for visual navigation"},{"key":"ref25","author":"sutton","year":"0","journal-title":"Reinforcement Learning An Introduction"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08460655.pdf?arnumber=8460655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T02:56:09Z","timestamp":1598237769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8460655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8460655","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}