{"list":"other","total":51,"rows":[{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302},{"id":"1806.06877","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","created":"2018-06-18","cited_by_count":298},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"1701.06049","title":"Interactive Learning from Policy-Dependent Human Feedback","created":"2017-01-21","cited_by_count":158},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144},{"id":"1709.10163","title":"Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces","created":"2017-09-28","cited_by_count":123},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106},{"id":"2203.10050","title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning","created":"2022-03-18","cited_by_count":97},{"id":"1810.04303","title":"Batch Active Preference-Based Learning of Reward Functions","created":"2018-10-10","cited_by_count":87},{"id":"2212.03363","title":"Few-Shot Preference Learning for Human-in-the-Loop RL","created":"2022-12-06","cited_by_count":87},{"id":"2010.11723","title":"Learning from Suboptimal Demonstration via Self-Supervised Reward Regression","created":"2020-10-17","cited_by_count":84},{"id":"2010.14500","title":"COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning","created":"2020-10-27","cited_by_count":83},{"id":"1802.05313","title":"Reinforcement Learning from Imperfect Demonstrations","created":"2018-02-14","cited_by_count":75},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71},{"id":"2006.14091","title":"Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences","created":"2020-06-24","cited_by_count":71},{"id":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64},{"id":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62},{"id":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61},{"id":"2206.02231","title":"Models of human preference for learning reward functions","created":"2022-06-05","cited_by_count":54},{"id":"2109.12750","title":"Learning Multimodal Rewards from Rankings","created":"2021-09-27","cited_by_count":41},{"id":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39},{"id":"2108.05382","title":"Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback","created":"2021-08-11","cited_by_count":35},{"id":"2110.12661","title":"ZerO Initialization: Initializing Neural Networks with only Zeros and Ones","created":"2021-10-25","cited_by_count":28},{"id":"2010.10181","title":"Robust Imitation Learning from Noisy Demonstrations","created":"2020-10-20","cited_by_count":26},{"id":"2312.09337","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","created":"2023-12-14","cited_by_count":26},{"id":"2110.00284","title":"Learning Reward Functions from Scale Feedback","created":"2021-10-01","cited_by_count":24},{"id":"2301.11774","title":"Reinforcement Learning from Diverse Human Preferences","created":"2023-01-27","cited_by_count":24},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21},{"id":"2211.06519","title":"The Expertise Problem: Learning from Specialized Feedback","created":"2022-11-12","cited_by_count":20},{"id":"2207.03395","title":"Unified Learning from Demonstrations, Corrections, and Preferences during Physical Human-Robot Interaction","created":"2022-07-07","cited_by_count":19},{"id":"2307.16348","title":"Rating-based Reinforcement Learning","created":"2023-07-30","cited_by_count":15},{"id":"2302.13507","title":"Active Reward Learning from Online Preferences","created":"2023-02-27","cited_by_count":13},{"id":"2303.00894","title":"Active Reward Learning from Multiple Teachers","created":"2023-03-02","cited_by_count":13},{"id":"2007.01038","title":"Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?","created":"2020-07-02","cited_by_count":12},{"id":"2404.08828","title":"Hindsight PRIORs for Reward Learning from Human Preferences","created":"2024-04-12","cited_by_count":12},{"id":"2306.03615","title":"PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation","created":"2023-06-06","cited_by_count":9},{"id":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9},{"id":"2309.03581","title":"Interactive Hyperparameter Optimization in Multi-Objective Problems via Preference Learning","created":"2023-09-07","cited_by_count":8},{"id":"2402.15420","title":"PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning","created":"2024-02-23","cited_by_count":8},{"id":"2201.00469","title":"Feedback-efficient Active Preference Learning for Socially Aware Robot Navigation","created":"2022-01-03","cited_by_count":7},{"id":"2303.04592","title":"Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skills","created":"2023-03-07","cited_by_count":6},{"id":"2310.06648","title":"Diversity from Human Feedback","created":"2023-10-10","cited_by_count":5},{"id":"2211.10861","title":"Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation","created":"2022-11-20","cited_by_count":4},{"id":"2302.08738","title":"Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning","created":"2023-02-17","cited_by_count":4},{"id":"2204.11897","title":"Reinforcement Teaching","created":"2022-04-25","cited_by_count":1}],"next_cursor":null}