Agent Systems

Self-Supervised Learning of Long-Horizon Manipulation Tasks with Finite-State Task Machines L4DC 2021 Semantic Audio-Visual Navigation CVPR 2021 SHAPELURN: An Interactive Language Learning Game with Logical Inference ACL 2021 Shaping embodied agent behavior with activity-context priors from egocentric video NeurIPS 2021 Sim and Real: Better Together NeurIPS 2021 Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy ICLR 2021 Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback CoRL 2021 Social Interactions as Recursive MDPs CoRL 2021 Software for Agent-based Network Simulation and Visualization AAAI 2021 SOON: Scenario Oriented Object Navigation With Graph-Based Exploration CVPR 2021 Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains NeurIPS 2021 Spatially Structured Recurrent Modules ICLR 2021 Stochastic model for sunk cost bias UAI 2021 Strategic Classification in the Dark ICML 2021 Structured deep generative models for sampling on constraint manifolds in sequential manipulation CoRL 2021 Structured Scene Memory for Vision-Language Navigation CVPR 2021 Surprisingly Robust In-Hand Manipulation: An Empirical Study RSS 2021 Symbol Grounding and Task Learning from Imperfect Corrections ACL 2021 Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations RSS 2021 TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators IJCAI 2021 Task-Driven Out-of-Distribution Detection with Statistical Guarantees for Robot Learning CoRL 2021 Task-Optimal Exploration in Linear Dynamical Systems ICML 2021 TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL ICML 2021 TempoRL: Learning When to Act ICML 2021 Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines AAAI 2021