Agent Systems

Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System NeurIPS 2021 Inverse Reinforcement Learning with Natural Language Goals AAAI 2021 INVIGORATE: Interactive Visual Grounding and Grasping in Clutter RSS 2021 Jerk-limited Real-time Trajectory Generation with Arbitrary Target States RSS 2021 Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning NeurIPS 2021 Language Grounding with 3D Objects CoRL 2021 Language Models are Few-Shot Butlers EMNLP 2021 Learning and Planning in Average-Reward Markov Decision Processes ICML 2021 Learning Generalizable Visual Representations via Interactive Gameplay ICLR 2021 Learning How to Solve “Bubble Ball” L4DC 2021 Learning Inertial Odometry for Dynamic Legged Robot State Estimation CoRL 2021 Learning Instance-Level N-Ary Semantic Knowledge At Scale For Robots Operating in Everyday Environments RSS 2021 Learning Invariant Representations for Reinforcement Learning without Reconstruction ICLR 2021 Learning Knowledge Graph-based World Models of Textual Environments NeurIPS 2021 Learning Mesh-Based Simulation with Graph Networks ICLR 2021 Learning Safe Multi-agent Control with Decentralized Neural Barrier Certificates ICLR 2021 Learning Subgoal Representations with Slow Dynamics ICLR 2021 Learning To Recommend Frame for Interactive Video Object Segmentation in the Wild CVPR 2021 Learning to Weight Imperfect Demonstrations ICML 2021 LEO: Learning Energy-based Models in Factor Graph Optimization CoRL 2021 Logarithmic Regret for Reinforcement Learning with Linear Function Approximation ICML 2021 Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy EMNLP 2021 Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks IJCAI 2021 Machine versus Human Attention in Deep Reinforcement Learning Tasks NeurIPS 2021 MADE: Exploration via Maximizing Deviation from Explored Regions NeurIPS 2021