{"list":"other","total":71,"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":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"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":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"1504.04909","title":"Illuminating search spaces by mapping elites","created":"2015-04-20","cited_by_count":425},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1709.10089","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","created":"2017-09-28","cited_by_count":340},{"id":"1707.08817","title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","created":"2017-07-27","cited_by_count":319},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229},{"id":"1407.3501","title":"Robots that can adapt like animals","created":"2014-07-13","cited_by_count":204},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161},{"id":"2002.03647","title":"Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills","created":"2020-02-10","cited_by_count":122},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112},{"id":"1712.06560","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","created":"2017-12-18","cited_by_count":107},{"id":"2302.00935","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","created":"2023-02-02","cited_by_count":104},{"id":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89},{"id":"1812.03381","title":"Learning Montezuma's Revenge from a Single Demonstration","created":"2018-12-08","cited_by_count":80},{"id":"2010.14484","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","created":"2020-10-27","cited_by_count":79},{"id":"2502.08844","title":"MuJoCo Playground","created":"2025-02-12","cited_by_count":78},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76},{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70},{"id":"1610.05729","title":"Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm","created":"2016-10-18","cited_by_count":66},{"id":"2311.02198","title":"Imitation Bootstrapped Reinforcement Learning","created":"2023-11-03","cited_by_count":64},{"id":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63},{"id":"2206.10787","title":"Global Planning for Contact-Rich Manipulation via Local Smoothing of Quasi-dynamic Contact Models","created":"2022-06-22","cited_by_count":49},{"id":"1704.02399","title":"Stein Variational Policy Gradient","created":"2017-04-07","cited_by_count":44},{"id":"2212.04180","title":"evosax: JAX-based Evolution Strategies","created":"2022-12-08","cited_by_count":41},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37},{"id":"1906.00088","title":"Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies","created":"2019-05-31","cited_by_count":34},{"id":"2205.08129","title":"Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space","created":"2022-05-17","cited_by_count":31},{"id":"1805.10309","title":"Learning Self-Imitating Diverse Policies","created":"2018-05-25","cited_by_count":29},{"id":"1910.02826","title":"Self-Paced Contextual Reinforcement Learning","created":"2019-10-07","cited_by_count":26},{"id":"2310.17966","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","created":"2023-10-27","cited_by_count":26},{"id":"2204.02246","title":"Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization","created":"2022-04-04","cited_by_count":23},{"id":"2210.03516","title":"Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery","created":"2022-10-06","cited_by_count":23},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23},{"id":"2206.03787","title":"Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance","created":"2022-06-08","cited_by_count":22},{"id":"2210.09622","title":"Deep Black-Box Reinforcement Learning with Movement Primitives","created":"2022-10-18","cited_by_count":20},{"id":"2303.03832","title":"MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy","created":"2023-03-07","cited_by_count":20},{"id":"2305.13795","title":"Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning","created":"2023-05-23","cited_by_count":20},{"id":"2212.02179","title":"Physics-Informed Model-Based Reinforcement Learning","created":"2022-12-05","cited_by_count":18},{"id":"2407.12448","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","created":"2024-07-17","cited_by_count":17},{"id":"2406.06615","title":"Language Guided Skill Discovery","created":"2024-06-07","cited_by_count":16},{"id":"2403.06966","title":"Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts","created":"2024-03-11","cited_by_count":14},{"id":"2409.14562","title":"DROP: Dexterous Reorientation via Online Planning","created":"2024-09-22","cited_by_count":14},{"id":"2403.09930","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","created":"2024-03-15","cited_by_count":13},{"id":"2207.05631","title":"DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization","created":"2022-07-12","cited_by_count":10},{"id":"2303.16207","title":"The Quality-Diversity Transformer: Generating Behavior-Conditioned Trajectories with Decision Transformers","created":"2023-03-27","cited_by_count":10},{"id":"2310.02440","title":"Learning Diverse Skills for Local Navigation under Multi-constraint Optimality","created":"2023-10-03","cited_by_count":8},{"id":"2407.09247","title":"Constrained Intrinsic Motivation for Reinforcement Learning","created":"2024-07-12","cited_by_count":6},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4},{"id":"2310.14509","title":"Iteratively Learn Diverse Strategies with State Distance Information","created":"2023-10-23","cited_by_count":3},{"id":"2402.00823","title":"SLIM: Skill Learning with Multiple Critics","created":"2024-02-01","cited_by_count":3},{"id":"2410.10390","title":"Stein Variational Evolution Strategies","created":"2024-10-14","cited_by_count":2},{"id":"2502.02190","title":"Discovering Quality-Diversity Algorithms via Meta-Black-Box Optimization","created":"2025-02-04","cited_by_count":2}],"next_cursor":null}