Agent Systems

Posterior Tracking Algorithm for Classification Bandits AISTATS 2023 Post-Processing Temporal Action Detection CVPR 2023 PourIt!: Weakly-Supervised Liquid Perception from a Single Image for Visual Closed-Loop Robotic Pouring ICCV 2023 PowRL: A Reinforcement Learning Framework for Robust Management of Power Networks AAAI 2023 Predicting Routine Object Usage for Proactive Robot Assistance CoRL 2023 Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons ICML 2023 Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty AAAI 2023 Programmatically Grounded, Compositionally Generalizable Robotic Manipulation ICLR 2023 Proportionally Fair Online Allocation of Public Goods with Predictions IJCAI 2023 Prototyping Logic-Based AI Services with LogicUS AAAI 2023 Provably Sample-Efficient Model-Free Algorithm for MDPs with Peak Constraints JMLR 2023 Push Past Green: Learning to Look Behind Plant Foliage by Moving It CoRL 2023 PyPose: A Library for Robot Learning With Physics-Based Optimization CVPR 2023 Quantifying Assistive Robustness Via the Natural-Adversarial Frontier CoRL 2023 R2H: Building Multimodal Navigation Helpers that Respond to Help Requests EMNLP 2023 ReAct: Synergizing Reasoning and Acting in Language Models ICLR 2023 Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals NeurIPS 2023 Reader: Model-based language-instructed reinforcement learning EMNLP 2023 Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans NeurIPS 2023 REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction CoRL 2023 Reflexion: language agents with verbal reinforcement learning NeurIPS 2023 Reinforcement Learning from Passive Data via Latent Intentions ICML 2023 Reinforcement Learning with History Dependent Dynamic Contexts ICML 2023 Reinforcement Learning with Simple Sequence Priors NeurIPS 2023 Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences ICLR 2023