{"list":"other","total":65,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"1703.07326","title":"One-Shot Imitation Learning","created":"2017-03-21","cited_by_count":233},{"id":"1709.04905","title":"One-Shot Visual Imitation Learning via Meta-Learning","created":"2017-09-14","cited_by_count":228},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170},{"id":"1802.01557","title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning","created":"2018-02-05","cited_by_count":148},{"id":"2010.12083","title":"Language-Conditioned Imitation Learning for Robot Manipulation Tasks","created":"2020-10-22","cited_by_count":136},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122},{"id":"1903.02020","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","created":"2019-03-05","cited_by_count":114},{"id":"2205.14204","title":"Multimodal Masked Autoencoders Learn Transferable Representations","created":"2022-05-27","cited_by_count":109},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"1805.11592","title":"Playing hard exploration games by watching YouTube","created":"2018-05-29","cited_by_count":99},{"id":"1912.02975","title":"Observational Overfitting in Reinforcement Learning","created":"2019-12-06","cited_by_count":91},{"id":"2302.02408","title":"Multi-View Masked World Models for Visual Robotic Manipulation","created":"2023-02-05","cited_by_count":80},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79},{"id":"2112.05219","title":"CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions","created":"2021-12-09","cited_by_count":78},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70},{"id":"2204.05186","title":"Correcting Robot Plans with Natural Language Feedback","created":"2022-04-11","cited_by_count":69},{"id":"2205.13115","title":"Fine-grained Image Captioning with CLIP Reward","created":"2022-05-26","cited_by_count":69},{"id":"2304.07297","title":"Language Instructed Reinforcement Learning for Human-AI Coordination","created":"2023-04-13","cited_by_count":63},{"id":"2005.09382","title":"Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text","created":"2020-05-19","cited_by_count":59},{"id":"2207.08229","title":"Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models","created":"2022-07-17","cited_by_count":45},{"id":"2212.03862","title":"Teaching Matters: Investigating the Role of Supervision in Vision Transformers","created":"2022-12-07","cited_by_count":45},{"id":"1908.05451","title":"Mapping State Space using Landmarks for Universal Goal Reaching","created":"2019-08-15","cited_by_count":44},{"id":"1911.01103","title":"Learning One-Shot Imitation from Humans without Humans","created":"2019-11-04","cited_by_count":33},{"id":"2306.16207","title":"Inferring the Goals of Communicating Agents from Actions and Instructions","created":"2023-06-28","cited_by_count":17}],"next_cursor":null}