{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"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":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"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":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662},{"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":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"1803.11175","title":"Universal Sentence Encoder","created":"2018-03-29","cited_by_count":489},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"2006.15134","title":"Critic Regularized Regression","created":"2020-06-26","cited_by_count":275},{"id":"2103.08050","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","created":"2021-03-14","cited_by_count":238},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229},{"id":"2002.08396","title":"Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning","created":"2020-02-19","cited_by_count":215},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2210.03370","title":"GNM: A General Navigation Model to Drive Any Robot","created":"2022-10-07","cited_by_count":171},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125},{"id":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118},{"id":"1903.03878","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","created":"2019-03-09","cited_by_count":107},{"id":"1912.02877","title":"Training Agents using Upside-Down Reinforcement Learning","created":"2019-12-05","cited_by_count":107},{"id":"1912.13465","title":"Reward-Conditioned Policies","created":"2019-12-31","cited_by_count":102},{"id":"1910.12179","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","created":"2019-10-27","cited_by_count":91},{"id":"2203.11931","title":"MetaMorph: Learning Universal Controllers with Transformers","created":"2022-03-22","cited_by_count":89},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89},{"id":"2011.05970","title":"Transformers for One-Shot Visual Imitation","created":"2020-11-11","cited_by_count":78},{"id":"2210.05178","title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","created":"2022-10-11","cited_by_count":78},{"id":"2206.01079","title":"When does return-conditioned supervised learning work for offline reinforcement learning?","created":"2022-06-02","cited_by_count":76},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71},{"id":"2109.10813","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","created":"2021-09-22","cited_by_count":69},{"id":"2106.03427","title":"Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring","created":"2021-06-07","cited_by_count":53},{"id":"1705.05035","title":"Discrete Sequential Prediction of Continuous Actions for Deep RL","created":"2017-05-14","cited_by_count":51},{"id":"2111.05424","title":"AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale","created":"2021-11-09","cited_by_count":44},{"id":"2004.06089","title":"Thinking While Moving: Deep Reinforcement Learning with Concurrent Control","created":"2020-04-13","cited_by_count":31},{"id":"2210.07432","title":"Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations","created":"2022-10-14","cited_by_count":14},{"id":"2211.01052","title":"Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints","created":"2022-11-02","cited_by_count":13},{"id":"2201.12594","title":"Robust Imitation Learning from Corrupted Demonstrations","created":"2022-01-29","cited_by_count":10},{"id":"1911.05864","title":"Motion Reasoning for Goal-Based Imitation Learning","created":"2019-11-13","cited_by_count":6}],"next_cursor":null}