{"list":"other","total":51,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"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":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197},{"id":"2108.03272","title":"iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks","created":"2021-08-06","cited_by_count":194},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177},{"id":"2004.12570","title":"The Ingredients of Real-World Robotic Reinforcement Learning","created":"2020-04-27","cited_by_count":117},{"id":"2010.14603","title":"Learning to be Safe: Deep RL with a Safety Critic","created":"2020-10-27","cited_by_count":116},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102},{"id":"2012.03912","title":"MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation","created":"2020-12-07","cited_by_count":95},{"id":"2104.11203","title":"Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention","created":"2021-04-22","cited_by_count":95},{"id":"1711.06782","title":"Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning","created":"2017-11-18","cited_by_count":90},{"id":"1901.10500","title":"Discretizing Continuous Action Space for On-Policy Optimization","created":"2019-01-29","cited_by_count":68},{"id":"2103.14025","title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","created":"2021-03-25","cited_by_count":65},{"id":"2008.12760","title":"AllenAct: A Framework for Embodied AI Research","created":"2020-08-28","cited_by_count":54},{"id":"2203.12677","title":"Vision-Based Manipulators Need to Also See from Their Hands","created":"2022-03-15","cited_by_count":47},{"id":"2012.03548","title":"Reset-Free Lifelong Learning with Skill-Space Planning","created":"2020-12-07","cited_by_count":38},{"id":"2303.01488","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","created":"2023-03-02","cited_by_count":34},{"id":"2107.12931","title":"Autonomous Reinforcement Learning via Subgoal Curricula","created":"2021-07-27","cited_by_count":33},{"id":"2112.09605","title":"Autonomous Reinforcement Learning: Formalism and Benchmarking","created":"2021-12-17","cited_by_count":33},{"id":"2011.05286","title":"Continual Learning of Control Primitives: Skill Discovery via Reset-Games","created":"2020-11-10","cited_by_count":29},{"id":"2212.09902","title":"Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance","created":"2022-12-19","cited_by_count":23},{"id":"2205.05212","title":"A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning","created":"2022-05-11","cited_by_count":22},{"id":"2210.10765","title":"When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning","created":"2022-10-19","cited_by_count":21},{"id":"2106.04480","title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning","created":"2021-06-08","cited_by_count":18},{"id":"2211.09960","title":"Ask4Help: Learning to Leverage an Expert for Embodied Tasks","created":"2022-11-18","cited_by_count":18},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16},{"id":"2203.15755","title":"Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning","created":"2022-03-29","cited_by_count":15},{"id":"2303.05508","title":"Cherry-Picking with Reinforcement Learning : Robust Dynamic Grasping in Unstable Conditions","created":"2023-03-09","cited_by_count":11},{"id":"2112.12612","title":"Towards Disturbance-Free Visual Mobile Manipulation","created":"2021-12-17","cited_by_count":6},{"id":"2203.08141","title":"Object Manipulation via Visual Target Localization","created":"2022-03-15","cited_by_count":6}],"next_cursor":null}