{"list":"other","total":53,"rows":[{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"1807.10299","title":"Variational Option Discovery Algorithms","created":"2018-07-26","cited_by_count":122},{"id":"1710.09767","title":"Meta Learning Shared Hierarchies","created":"2017-10-26","cited_by_count":93},{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67},{"id":"2202.00914","title":"Lipschitz-constrained Unsupervised Skill Discovery","created":"2022-02-02","cited_by_count":62},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53},{"id":"2207.07560","title":"Skill-based Model-based Reinforcement Learning","created":"2022-07-15","cited_by_count":50},{"id":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49},{"id":"1910.04450","title":"Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards","created":"2019-10-10","cited_by_count":40},{"id":"1806.04640","title":"Unsupervised Meta-Learning for Reinforcement Learning","created":"2018-06-12","cited_by_count":39},{"id":"2107.14226","title":"Learning more skills through optimistic exploration","created":"2021-07-29","cited_by_count":38},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38},{"id":"2204.11828","title":"Skill-based Meta-Reinforcement Learning","created":"2022-04-25","cited_by_count":37},{"id":"2206.10442","title":"Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning","created":"2022-06-21","cited_by_count":35},{"id":"1810.11583","title":"Learning Abstract Options","created":"2018-10-27","cited_by_count":31},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28},{"id":"2006.07178","title":"Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling","created":"2020-06-12","cited_by_count":26},{"id":"2206.09314","title":"Robust Imitation Learning against Variations in Environment Dynamics","created":"2022-06-19","cited_by_count":26},{"id":"2102.12571","title":"The Logical Options Framework","created":"2021-02-24","cited_by_count":25},{"id":"2211.02231","title":"Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics","created":"2022-11-04","cited_by_count":24},{"id":"2006.01419","title":"Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration","created":"2020-06-02","cited_by_count":20},{"id":"2310.20287","title":"Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents","created":"2023-10-31","cited_by_count":12},{"id":"2312.15909","title":"Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations","created":"2023-12-26","cited_by_count":10},{"id":"2308.11272","title":"FoX: Formation-aware exploration in multi-agent reinforcement learning","created":"2023-08-22","cited_by_count":9},{"id":"2112.00901","title":"Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL","created":"2021-12-02","cited_by_count":8},{"id":"2206.03597","title":"Meta-Learning Parameterized Skills","created":"2022-06-07","cited_by_count":7},{"id":"2209.15205","title":"ASPiRe:Adaptive Skill Priors for Reinforcement Learning","created":"2022-09-30","cited_by_count":7},{"id":"2312.07392","title":"ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning","created":"2023-12-12","cited_by_count":6},{"id":"2502.02844","title":"Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning","created":"2025-02-05","cited_by_count":6},{"id":"2110.09507","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","created":"2021-10-18","cited_by_count":5},{"id":"2109.09031","title":"Hindsight Foresight Relabeling for Meta-Reinforcement Learning","created":"2021-09-18","cited_by_count":4},{"id":"2312.06518","title":"Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills","created":"2023-12-11","cited_by_count":4},{"id":"2410.07933","title":"Offline Hierarchical Reinforcement Learning via Inverse Optimization","created":"2024-10-10","cited_by_count":4},{"id":"2408.15593","title":"Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning","created":"2024-08-28","cited_by_count":3},{"id":"2402.07418","title":"SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation","created":"2024-02-12","cited_by_count":2},{"id":"1909.13607","title":"MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning","created":"2019-09-30","cited_by_count":1}],"next_cursor":null}