Abstract is missing.
- Data Efficient Reinforcement Learning for Legged RobotsYuxiang Yang, Ken Caluwaerts, Atil Iscen, Tingnan Zhang, Jie Tan, Vikas Sindhwani. 1-10 [doi]
- To Follow or not to Follow: Selective Imitation Learning from ObservationsYoungwoon Lee, Edward S. Hu, Zhengyu Yang, Joseph J. Lim. 11-23 [doi]
- On-Policy Robot Imitation Learning from a Converging SupervisorAshwin Balakrishna, Brijen Thananjeyan, Jonathan Lee, Felix Li, Arsh Zahed, Joseph E. Gonzalez, Ken Goldberg. 24-41 [doi]
- Dynamics Learning with Cascaded Variational Inference for Multi-Step ManipulationKuan Fang, Yuke Zhu, Animesh Garg, Silvio Savarese, Fei-Fei Li 0001. 42-52 [doi]
- S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered ScenesYuzhe Qin, Rui Chen, Hao Zhu, Meng Song, Jing Xu, Hao Su. 53-65 [doi]
- Learning by CheatingDian Chen 0001, Brady Zhou, Vladlen Koltun, Philipp Krähenbühl. 66-75 [doi]
- Multimodal Attention Branch Network for Perspective-Free Sentence GenerationAly Magassouba, Komei Sugiura, Hisashi Kawai. 76-85 [doi]
- MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior PredictionYuning Chai, Benjamin Sapp, Mayank Bansal, Dragomir Anguelov. 86-99 [doi]
- Object-centric Forward Modeling for Model Predictive ControlYufei Ye, Dhiraj Gandhi, Abhinav Gupta 0001, Shubham Tulsiani. 100-109 [doi]
- Multi-Agent Manipulation via Locomotion using Hierarchical Sim2RealOfir Nachum, Michael Ahn, Hugo Ponte, Shixiang Shane Gu, Vikash Kumar. 110-121 [doi]
- Combining Deep Learning and Verification for Precise Object Instance DetectionSiddharth Ancha, Junyu Nan, David Held. 122-141 [doi]
- MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement LearningBohan Wu, Iretiayo Akinola, Jacob Varley, Peter K. Allen. 142-161 [doi]
- Curious iLQR: Resolving Uncertainty in Model-based RLSarah Bechtle, Yixin Lin, Akshara Rai, Ludovic Righetti, Franziska Meier. 162-171 [doi]
- Hybrid system identification using switching density networksMichael Burke, Yordan Hristov, Subramanian Ramamoorthy. 172-181 [doi]
- Regularizing Model-Based Planning with Energy-Based ModelsRinu Boney, Juho Kannala, Alexander Ilin. 182-191 [doi]
- Semi-Supervised Learning of Decision-Making Models for Human-Robot CollaborationVaibhav V. Unhelkar, Shen Li, Julie A. Shah. 192-203 [doi]
- Riemannian Motion Policy Fusion through Learnable Lyapunov Function ReshapingMustafa Mukadam, Ching-An Cheng, Dieter Fox, Byron Boots, Nathan D. Ratliff. 204-219 [doi]
- Perceptual Attention-based Predictive ControlKeuntaek Lee, Gabriel Nakajima An, Viacheslav Zakharov, Evangelos A. Theodorou. 220-232 [doi]
- Bayesian Optimization Meets Riemannian Manifolds in Robot LearningNoémie Jaquier, Leonel Dario Rozo, Sylvain Calinon, Mathias Bürger. 233-246 [doi]
- Learning from demonstration with model-based Gaussian processNoémie Jaquier, David Ginsbourger, Sylvain Calinon. 247-257 [doi]
- Variational Inference MPC for Bayesian Model-based Reinforcement LearningMasashi Okada, Tadahiro Taniguchi. 258-272 [doi]
- Optimizing Sequences of Probabilistic Manipulation Skills Learned from DemonstrationLukas Schwenkel, Meng Guo, Mathias Bürger. 273-282 [doi]
- Predictive Safety Network for Resource-constrained Multi-agent SystemsMeng Guo, Mathias Bürger. 283-292 [doi]
- A correct formulation for the Orientation Dynamic Movement Primitives for robot control in the Cartesian spaceLeonidas Koutras, Zoe Doulgeri. 293-302 [doi]
- Masking by Moving: Learning Distraction-Free Radar Odometry from Pose InformationDan Barnes, Rob Weston, Ingmar Posner. 303-316 [doi]
- Learning Locomotion Skills for Cassie: Iterative Design and Sim-to-RealZhaoming Xie, Patrick Clary, Jeremy Dao, Pedro Morais, Jonanthan Hurst, Michiel van de Panne. 317-329 [doi]
- Better-than-Demonstrator Imitation Learning via Automatically-Ranked DemonstrationsDaniel S. Brown, Wonjoon Goo, Scott Niekum. 330-359 [doi]
- Mutual-Information Regularization in Markov Decision Processes and Actor-Critic LearningFelix Leibfried, Jordi Grau-Moya. 360-373 [doi]
- Model-Based Planning with Energy-Based ModelsYilun Du, Toru Lin, Igor Mordatch. 374-383 [doi]
- Identifying Unknown Instances for Autonomous DrivingKelvin Wong, Shenlong Wang, Mengye Ren, Ming Liang, Raquel Urtasun. 384-393 [doi]
- Vision-and-Dialog NavigationJesse Thomason, Michael Murray, Maya Cakmak, Luke Zettlemoyer. 394-406 [doi]
- Discrete Residual Flow for Probabilistic Pedestrian Behavior PredictionAjay Jain, Sergio Casas 0002, Renjie Liao, Yuwen Xiong, Song Feng, Sean Segal, Raquel Urtasun. 407-419 [doi]
- Combining Optimal Control and Learning for Visual Navigation in Novel EnvironmentsSomil Bansal, Varun Tolani, Saurabh Gupta 0001, Jitendra Malik, Claire Tomlin. 420-429 [doi]
- Leveraging exploration in off-policy algorithms via normalizing flowsBogdan Mazoure, Thang Doan, Audrey Durand, Joelle Pineau, R. Devon Hjelm. 430-444 [doi]
- TuneNet: One-Shot Residual Tuning for System Identification and Sim-to-Real Robot Task TransferAdam Allevato, Elaine Schaertl Short, Mitch Pryor, Andrea Thomaz. 445-455 [doi]
- Bayesian Optimization in Variational Latent Spaces with Dynamic CompressionRika Antonova, Akshara Rai, Tianyu Li, Danica Kragic. 456-465 [doi]
- A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World RobotsNicolai A. Lynnerup, Laura Nolling, Rasmus Hasle, John Hallam. 466-489 [doi]
- Learning to Manipulate Object Collections Using Grounded State RepresentationsMatthew Wilson, Tucker Hermans. 490-502 [doi]
- Robust Semi-Supervised Monocular Depth Estimation with Reprojected DistancesVitor Guizilini, Jie Li, Rares Ambrus, Sudeep Pillai, Adrien Gaidon. 503-512 [doi]
- Self-Paced Contextual Reinforcement LearningPascal Klink, Hany Abdulsamad, Boris Belousov, Jan Peters 0001. 513-529 [doi]
- Contextual Imagined Goals for Self-Supervised Robotic LearningAshvin Nair, Shikhar Bahl, Alexander Khazatsky, Vitchyr Pong, Glen Berseth, Sergey Levine. 530-539 [doi]
- Conditional Driving from Natural Language InstructionsJunha Roh, Chris Paxton, Andrzej Pronobis, Ali Farhadi, Dieter Fox. 540-551 [doi]
- Adversarial Active Exploration for Inverse Dynamics Model LearningZhang-Wei Hong, Tsu-Jui Fu, Tzu-Yun Shann, Chun-Yi Lee. 552-565 [doi]
- Imagined Value Gradients: Model-Based Policy Optimization with Tranferable Latent Dynamics ModelsArunkumar Byravan, Jost Tobias Springenberg, Abbas Abdolmaleki, Roland Hafner, Michael Neunert, Thomas Lampe, Noah Siegel, Nicolas Heess, Martin A. Riedmiller. 566-589 [doi]
- PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement LearningIou-Jen Liu, Raymond A. Yeh, Alexander G. Schwing. 590-602 [doi]
- HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile ManipulatorsChengshu Li, Fei Xia, Roberto Martín-Martín, Silvio Savarese. 603-616 [doi]
- Learning Navigation Subroutines from Egocentric VideosAshish Kumar, Saurabh Gupta 0001, Jitendra Malik. 617-626 [doi]
- A Learnable Safety MeasureSteve Heim, Alexander von Rohr, Sebastian Trimpe, Alexander Badri-Spröwitz. 627-639 [doi]
- HJB Optimal Feedback Control with Deep Differential Value Functions and Action ConstraintsMichael Lutter, Boris Belousov, Kim Listmann, Debora Clever, Jan Peters 0001. 640-650 [doi]
- Multi-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low LightEunah Jung, Nan Yang 0007, Daniel Cremers. 651-660 [doi]
- Connectivity Guaranteed Multi-robot Navigation via Deep Reinforcement LearningJuntong Lin, Xuyun Yang, Peiwei Zheng, Hui Cheng. 661-670 [doi]
- Learning Decentralized Controllers for Robot Swarms with Graph Neural NetworksEkaterina V. Tolstaya, Fernando Gama, James Paulos, George J. Pappas, Vijay Kumar 0001, Alejandro Ribeiro. 671-682 [doi]
- Provably Robust Blackbox Optimization for Reinforcement LearningKrzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Deepali Jain, Yuxiang Yang, Atil Iscen, Jasmine Hsu, Vikas Sindhwani. 683-696 [doi]
- Stochastic Optimal Control as Approximate Input InferenceJoe Watson, Hany Abdulsamad, Jan Peters 0001. 697-716 [doi]
- AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal TeachersAndrey Kurenkov, Ajay Mandlekar, Roberto Martin Martin, Silvio Savarese, Animesh Garg. 717-734 [doi]
- Continuous-Discrete Reinforcement Learning for Hybrid Control in RoboticsMichael Neunert, Abbas Abdolmaleki, Markus Wulfmeier, Thomas Lampe, Jost Tobias Springenberg, Roland Hafner, Francesco Romano, Jonas Buchli, Nicolas Heess, Martin A. Riedmiller. 735-751 [doi]
- Learning from My Partner's Actions: Roles in Decentralized Robot TeamsDylan P. Losey, Mengxi Li, Jeannette Bohg, Dorsa Sadigh. 752-765 [doi]
- Energy-efficient Path Planning for Ground Robots by and Combining Air and Ground MeasurementsMinghan Wei, Volkan Isler. 766-775 [doi]
- Multi-Agent Reinforcement Learning with Multi-Step Generative ModelsOrr Krupnik, Igor Mordatch, Aviv Tamar. 776-790 [doi]
- Learning to Navigate Using Mid-Level Visual PriorsAlexander Sax, Jeffrey O. Zhang, Bradley Emi, Amir Roshan Zamir, Silvio Savarese, Leonidas J. Guibas, Jitendra Malik. 791-812 [doi]
- Learning Compact Models for Planning with Exogenous ProcessesRohan Chitnis, Tomás Lozano-Pérez. 813-822 [doi]
- Graph Policy Gradients for Large Scale Robot ControlArbaaz Khan, Ekaterina V. Tolstaya, Alejandro Ribeiro, Vijay Kumar 0001. 823-834 [doi]
- Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentsRémy Portelas, Cédric Colas, Katja Hofmann, Pierre-Yves Oudeyer. 835-853 [doi]
- Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement LearningKevin Sebastian Luck, Heni Ben Amor, Roberto Calandra. 854-869 [doi]
- Disentangled Relational Representations for Explaining and Learning from DemonstrationYordan Hristov, Daniel Angelov, Michael Burke, Alex Lascarides, Subramanian Ramamoorthy. 870-884 [doi]
- RoboNet: Large-Scale Multi-Robot LearningSudeep Dasari, Frederik Ebert, Stephen Tian, Suraj Nair, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Sergey Levine, Chelsea Finn. 885-897 [doi]
- Counter-example Guided Learning of Bounds on Environment BehaviorYuxiao Chen, Sumanth Dathathri, Tung Phan-Minh, Richard M. Murray. 898-909 [doi]
- MAME : Model-Agnostic Meta-ExplorationSwaminathan Gurumurthy, Sumit Kumar, Katia P. Sycara. 910-922 [doi]
- End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point CloudsYin Zhou, Pei Sun, Yu Zhang, Dragomir Anguelov, Jiyang Gao, Tom Ouyang, James Guo, Jiquan Ngiam, Vijay Vasudevan. 923-932 [doi]
- Task-Conditioned Variational Autoencoders for Learning Movement PrimitivesMichael Noseworthy, Rohan Paul, Subhro Roy, Daehyung Park, Nicholas Roy. 933-944 [doi]
- Quasi-Newton Trust Region Policy OptimizationDevesh K. Jha, Arvind U. Raghunathan, Diego Romeres. 945-954 [doi]
- Learning value functions with relational state representations for guiding task-and-motion planningBeomjoon Kim, Luke Shimanuki. 955-968 [doi]
- Locally Weighted Regression Pseudo-Rehearsal for Adaptive Model Predictive ControlGrady R. Williams, Brian Goldfain, Keuntaek Lee, Jason Gibson, James M. Rehg, Evangelos A. Theodorou. 969-978 [doi]
- Graph-Structured Visual ImitationMaximilian Sieb, Xian Zhou, Audrey Huang, Oliver Kroemer, Katerina Fragkiadaki. 979-989 [doi]
- Deep Value Model Predictive ControlDavid Hoeller, Farbod Farshidian, Marco Hutter 0001. 990-1004 [doi]
- Inferring Task Goals and Constraints using Bayesian Nonparametric Inverse Reinforcement LearningDaehyung Park, Michael Noseworthy, Rohan Paul, Subhro Roy, Nicholas Roy. 1005-1014 [doi]
- Experience-Embedded Visual ForesightYen-Chen Lin, Maria Bauzá, Phillip Isola. 1015-1024 [doi]
- Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement LearningAbhishek Gupta 0004, Vikash Kumar, Corey Lynch, Sergey Levine, Karol Hausman. 1025-1037 [doi]
- Nonverbal Robot Feedback for Human TeachersSandy H. Huang, Isabella Huang, Ravi Pandya, Anca D. Dragan. 1038-1051 [doi]
- Two Stream Networks for Self-Supervised Ego-Motion EstimationRares Ambrus, Vitor Guizilini, Jie Li, Sudeep Pillai, Adrien Gaidon. 1052-1061 [doi]
- Model-based Behavioral Cloning with Future Image Similarity LearningAlan Wu, A. J. Piergiovanni, Michael S. Ryoo. 1062-1077 [doi]
- Worst Cases Policy GradientsYichuan Charlie Tang, Jian Zhang, Ruslan Salakhutdinov. 1078-1093 [doi]
- Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement LearningTianhe Yu, Deirdre Quillen, Zhanpeng He, Ryan Julian, Karol Hausman, Chelsea Finn, Sergey Levine. 1094-1100 [doi]
- Deep Dynamics Models for Learning Dexterous ManipulationAnusha Nagabandi, Kurt Konolige, Sergey Levine, Vikash Kumar. 1101-1112 [doi]
- Learning Latent Plans from PlayCorey Lynch, Mohi Khansari, Ted Xiao, Vikash Kumar, Jonathan Tompson, Sergey Levine, Pierre Sermanet. 1113-1132 [doi]
- Scene-level Pose Estimation for Multiple Instances of Densely Packed ObjectsChaitanya Mitash, Bowen Wen, Kostas E. Bekris, Abdeslam Boularias. 1133-1145 [doi]
- Macro-Action-Based Deep Multi-Agent Reinforcement LearningYuchen Xiao, Joshua Hoffman, Christopher Amato. 1146-1161 [doi]
- Active Domain RandomizationBhairav Mehta, Manfred Diaz, Florian Golemo, Christopher J. Pal, Liam Paull. 1162-1176 [doi]
- Asking Easy Questions: A User-Friendly Approach to Active Reward LearningErdem Biyik, Malayandi Palan, Nicholas C. Landolfi, Dylan P. Losey, Dorsa Sadigh. 1177-1190 [doi]
- Dynamic Experience ReplayJieliang Luo, Hui Li. 1191-1200 [doi]
- Language-guided Semantic Mapping and Mobile Manipulation in Partially Observable EnvironmentsSiddharth Patki, Ethan Fahnestock, Thomas M. Howard, Matthew R. Walter. 1201-1210 [doi]
- Learning Parametric Constraints in High Dimensions from DemonstrationsGlen Chou, Necmiye Ozay, Dmitry Berenson. 1211-1230 [doi]
- Variational Optimization Based Reinforcement Learning for Infinite Dimensional Stochastic SystemsEthan N. Evans, Marcus A. Periera, George I. Boutselis, Evangelos A. Theodorou. 1231-1246 [doi]
- Understanding Teacher Gaze Patterns for Robot LearningAkanksha Saran, Elaine Schaertl Short, Andrea Thomaz, Scott Niekum. 1247-1258 [doi]
- A Divergence Minimization Perspective on Imitation Learning MethodsSeyed Kamyar Seyed Ghasemipour, Richard S. Zemel, Shixiang Gu. 1259-1277 [doi]
- Receding Horizon CuriosityMatthias Schultheis, Boris Belousov, Hany Abdulsamad, Jan Peters 0001. 1278-1288 [doi]
- Learning to Generalize Kinematic Models to Novel ObjectsBen Abbatematteo, Stefanie Tellex, George Konidaris. 1289-1299 [doi]
- ROBEL: Robotics Benchmarks for Learning with Low-Cost RobotsMichael Ahn, Henry Zhu, Kristian Hartikainen, Hugo Ponte, Abhishek Gupta 0004, Sergey Levine, Vikash Kumar. 1300-1313 [doi]
- Navigation Agents for the Visually Impaired: A Sidewalk Simulator and ExperimentsMartin Weiss, Simon Chamorro, Roger Girgis, Margaux Luck, Samira Ebrahimi Kahou, Joseph Paul Cohen, Derek Nowrouzezahrai, Doina Precup, Florian Golemo, Chris Pal. 1314-1327 [doi]
- Certified Adversarial Robustness for Deep Reinforcement LearningBjörn Lütjens, Michael Everett, Jonathan P. How. 1328-1337 [doi]
- Asynchronous Methods for Model-Based Reinforcement LearningYunzhi Zhang, Ignasi Clavera, Boren Tsai, Pieter Abbeel. 1338-1347 [doi]
- PyRoboLearn: A Python Framework for Robot Learning PractitionersBrian Delhaisse, Leonel Dario Rozo, Darwin G. Caldwell. 1348-1358 [doi]
- An Online Learning Procedure for Feedback Linearization Control without Torque MeasurementsM. Capotondi, G. Turrisi, C. Gaz, Valerio Modugno, Giuseppe Oriolo, A. de Luca. 1359-1368 [doi]
- The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance SegmentationChristopher Xie, Yu Xiang, Arsalan Mousavian, Dieter Fox. 1369-1378 [doi]
- Trajectory-wise Control Variates for Variance Reduction in Policy Gradient MethodsChing-An Cheng, Xinyan Yan, Byron Boots. 1379-1394 [doi]
- Towards Learning to Detect and Predict Contact Events on Vision-based Tactile SensorsYazhan Zhang, Weihao Yuan, Zicheng Kan, Michael Yu Wang. 1395-1404 [doi]
- Kernel Trajectory Maps for Multi-Modal Probabilistic Motion PredictionWeiming Zhi, Lionel Ott, Fabio Ramos. 1405-1414 [doi]
- Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated FlightValts Blukis, Yannick Terme, Eyvind Niklasson, Ross A. Knepper, Yoav Artzi. 1415-1438 [doi]
- Entity Abstraction in Visual Model-Based Reinforcement LearningRishi Veerapaneni, John D. Co-Reyes, Michael Chang 0003, Michael Janner, Chelsea Finn, Jiajun Wu 0001, Joshua B. Tenenbaum, Sergey Levine. 1439-1456 [doi]
- Learning Reactive Motion Policies in Multiple Task Spaces from Human DemonstrationsMuhammad Asif Rana, Anqi Li, Harish Ravichandar, Mustafa Mukadam, Sonia Chernova, Dieter Fox, Byron Boots, Nathan D. Ratliff. 1457-1468 [doi]