Robotics

Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems ICML 2022 Interactron: Embodied Adaptive Object Detection CVPR 2022 Iterative Residual Policy for Goal-Conditioned Dynamic Manipulation of Deformable Objects RSS 2022 Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics ICML 2022 Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network NeurIPS 2022 Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding NeurIPS 2022 Learning Deep Input-Output Stable Dynamics NeurIPS 2022 Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization AAAI 2022 LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training EMNLP 2022 Low-Rank Modular Reinforcement Learning via Muscle Synergy NeurIPS 2022 LyaNet: A Lyapunov Framework for Training Neural ODEs ICML 2022 Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control ICML 2022 Marginal MAP estimation for inverse RL under occlusion with observer noise UAI 2022 Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification NeurIPS 2022 MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge NeurIPS 2022 MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control NeurIPS 2022 ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias ICML 2022 Multi-Sacle Dynamic Coding Improved Spiking Actor Network for Reinforcement Learning AAAI 2022 NeMF: Neural Motion Fields for Kinematic Animation NeurIPS 2022 Neural Circuit Architectural Priors for Embodied Control NeurIPS 2022 Neural Inertial Localization CVPR 2022 Neural Stochastic Control NeurIPS 2022 NICE-SLAM: Neural Implicit Scalable Encoding for SLAM CVPR 2022 One Step at a Time: Long-Horizon Vision-and-Language Navigation With Milestones CVPR 2022 On Optimizing Interventions in Shared Autonomy AAAI 2022