{"total":109,"rows":[{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165,"area":null},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149,"area":null},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2111.01674","title":"Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots","created":"2021-10-25","cited_by_count":76,"area":null},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70,"area":null},{"id":"2205.15299","title":"Adapting Rapid Motor Adaptation for Bipedal Robots","created":"2022-05-30","cited_by_count":54,"area":null},{"id":"2209.05309","title":"GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots","created":"2022-09-12","cited_by_count":48,"area":null},{"id":"2302.09450","title":"Robust and Versatile Bipedal Jumping Control through Reinforcement Learning","created":"2023-02-19","cited_by_count":36,"area":null},{"id":"2107.13545","title":"Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation","created":"2021-07-28","cited_by_count":35,"area":null},{"id":"2203.02638","title":"Safe Reinforcement Learning for Legged Locomotion","created":"2022-03-05","cited_by_count":35,"area":null},{"id":"2109.09180","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","created":"2021-09-19","cited_by_count":34,"area":null},{"id":"2303.01488","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2107.12931","title":"Autonomous Reinforcement Learning via Subgoal Curricula","created":"2021-07-27","cited_by_count":33,"area":null},{"id":"2304.09834","title":"Learning and Adapting Agile Locomotion Skills by Transferring Experience","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2101.07012","title":"Regularized Policies are Reward Robust","created":"2021-01-18","cited_by_count":32,"area":null},{"id":"2203.17138","title":"Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors","created":"2022-03-31","cited_by_count":30,"area":null},{"id":"2203.05194","title":"Learning Torque Control for Quadrupedal Locomotion","created":"2022-03-10","cited_by_count":29,"area":null},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2203.12759","title":"Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots","created":"2022-03-23","cited_by_count":22,"area":null},{"id":"2206.13316","title":"Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning","created":"2022-06-27","cited_by_count":22,"area":null},{"id":"2107.09822","title":"Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics","created":"2021-07-21","cited_by_count":20,"area":null},{"id":"2210.05150","title":"DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning","created":"2022-10-11","cited_by_count":19,"area":null},{"id":"2210.02317","title":"Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2309.03315","title":"Robotic Table Tennis: A Case Study into a High Speed Learning System","created":"2023-09-06","cited_by_count":13,"area":null},{"id":"2106.00517","title":"Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment","created":"2021-06-01","cited_by_count":12,"area":null},{"id":"2107.05686","title":"The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents","created":"2021-07-12","cited_by_count":12,"area":null},{"id":"2108.03718","title":"Meta-Reinforcement Learning in Broad and Non-Parametric Environments","created":"2021-08-08","cited_by_count":10,"area":null},{"id":"2103.02287","title":"Addressing Action Oscillations through Learning Policy Inertia","created":"2021-03-03","cited_by_count":9,"area":null},{"id":"2109.03188","title":"Optimizing Quantum Variational Circuits with Deep Reinforcement Learning","created":"2021-09-07","cited_by_count":9,"area":null},{"id":"2309.15293","title":"Maximum diffusion reinforcement learning","created":"2023-09-26","cited_by_count":9,"area":null},{"id":"2103.05981","title":"Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme","created":"2021-03-10","cited_by_count":8,"area":null},{"id":"2109.11767","title":"Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience","created":"2021-09-24","cited_by_count":8,"area":null},{"id":"2303.09597","title":"Residual Physics Learning and System Identification for Sim-to-real Transfer of Policies on Buoyancy Assisted Legged Robots","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2310.08702","title":"ELDEN: Exploration via Local Dependencies","created":"2023-10-12","cited_by_count":8,"area":null},{"id":"2407.08626","title":"RoboMorph: Evolving Robot Morphology using Large Language Models","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2105.12204","title":"Safe Value Functions","created":"2021-05-25","cited_by_count":7,"area":null},{"id":"2406.14655","title":"HYPERmotion: Learning Hybrid Behavior Planning for Autonomous Loco-manipulation","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2104.13617","title":"End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning","created":"2021-04-28","cited_by_count":6,"area":null},{"id":"2108.13525","title":"Identifying optimal cycles in quantum thermal machines with reinforcement-learning","created":"2021-08-30","cited_by_count":6,"area":null},{"id":"2204.08647","title":"Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation","created":"2022-04-19","cited_by_count":6,"area":null},{"id":"2209.11123","title":"Modern Machine Learning Tools for Monitoring and Control of Industrial Processes: A Survey","created":"2022-09-22","cited_by_count":6,"area":null},{"id":"2305.02054","title":"Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning","created":"2023-05-03","cited_by_count":6,"area":null},{"id":"2306.17101","title":"Identifying Important Sensory Feedback for Learning Locomotion Skills","created":"2023-06-29","cited_by_count":6,"area":null},{"id":"2508.08982","title":"Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion","created":"2025-08-12","cited_by_count":6,"area":null},{"id":"2105.01595","title":"Self-Improving Semantic Perception for Indoor Localisation","created":"2021-05-04","cited_by_count":5,"area":null},{"id":"2109.14026","title":"Learning Perceptual Locomotion on Uneven Terrains using Sparse Visual Observations","created":"2021-09-28","cited_by_count":5,"area":null},{"id":"2110.14998","title":"An Adaptable Approach to Learn Realistic Legged Locomotion without Examples","created":"2021-10-28","cited_by_count":5,"area":null},{"id":"2203.02230","title":"Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning","created":"2022-03-04","cited_by_count":5,"area":null},{"id":"2207.10106","title":"World Robot Challenge 2020 -- Partner Robot: A Data-Driven Approach for Room Tidying with Mobile Manipulator","created":"2022-07-20","cited_by_count":5,"area":null},{"id":"2209.11275","title":"Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learning","created":"2022-09-22","cited_by_count":5,"area":null},{"id":"2309.04974","title":"Continual Robot Learning using Self-Supervised Task Inference","created":"2023-09-10","cited_by_count":5,"area":null},{"id":"2501.16368","title":"Foundation Models for CPS-IoT: Opportunities and Challenges","created":"2025-01-22","cited_by_count":5,"area":null},{"id":"2210.00140","title":"Efficiently Learning Small Policies for Locomotion and Manipulation","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2305.05760","title":"Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization","created":"2023-05-09","cited_by_count":4,"area":null},{"id":"2309.16663","title":"HyperPPO: A scalable method for finding small policies for robotic control","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2404.10017","title":"Model-based Offline Quantum Reinforcement Learning","created":"2024-04-14","cited_by_count":4,"area":null},{"id":"2201.05599","title":"Smart Magnetic Microrobots Learn to Swim with Deep Reinforcement Learning","created":"2022-01-14","cited_by_count":3,"area":null},{"id":"2201.08115","title":"Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning","created":"2022-01-20","cited_by_count":3,"area":null},{"id":"2203.00368","title":"Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization","created":"2022-03-01","cited_by_count":3,"area":null},{"id":"2210.08065","title":"Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2306.04781","title":"Learning to Navigate in Turbulent Flows with Aerial Robot Swarms: A Cooperative Deep Reinforcement Learning Approach","created":"2023-06-07","cited_by_count":3,"area":null},{"id":"2307.16676","title":"End-to-End Reinforcement Learning for Torque Based Variable Height Hopping","created":"2023-07-31","cited_by_count":3,"area":null},{"id":"2309.04459","title":"Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2310.10606","title":"BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuning","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2312.05332","title":"MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control","created":"2023-12-08","cited_by_count":3,"area":null},{"id":"2406.15508","title":"What Teaches Robots to Walk, Teaches Them to Trade too -- Regime Adaptive Execution using Informed Data and LLMs","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2107.02955","title":"Quadruped Locomotion on Non-Rigid Terrain using Reinforcement Learning","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2107.04457","title":"Aligning an optical interferometer with beam divergence control and continuous action space","created":"2021-07-09","cited_by_count":2,"area":null},{"id":"2108.06911","title":"Optimal Actor-Critic Policy with Optimized Training Datasets","created":"2021-08-16","cited_by_count":2,"area":null},{"id":"2110.10255","title":"A Simple Approach to Continual Learning by Transferring Skill Parameters","created":"2021-10-19","cited_by_count":2,"area":null},{"id":"2207.07791","title":"Associative Memory Based Experience Replay for Deep Reinforcement Learning","created":"2022-07-16","cited_by_count":2,"area":null},{"id":"2209.07096","title":"Multi-Objective Policy Gradients with Topological Constraints","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2211.11620","title":"Simultaneously Updating All Persistence Values in Reinforcement Learning","created":"2022-11-21","cited_by_count":2,"area":null},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2401.07056","title":"Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics through Multi-Agent Reinforcement Learning Algorithms","created":"2024-01-13","cited_by_count":2,"area":null},{"id":"2402.00044","title":"Training microrobots to swim by a large language model","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2103.07616","title":"RL-Controller: a reinforcement learning framework for active structural control","created":"2021-03-13","cited_by_count":1,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2109.12696","title":"PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotion","created":"2021-09-26","cited_by_count":1,"area":null},{"id":"2112.05299","title":"Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots","created":"2021-12-10","cited_by_count":1,"area":null},{"id":"2204.04785","title":"Model-free optimization of power/efficiency tradeoffs in quantum thermal machines using reinforcement learning","created":"2022-04-10","cited_by_count":1,"area":null},{"id":"2305.19111","title":"GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts","created":"2023-05-30","cited_by_count":1,"area":null},{"id":"2310.11075","title":"Sim-to-Real Transfer of Adaptive Control Parameters for AUV Stabilization under Current Disturbance","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2408.15328","title":"Artificially intelligent Maxwell's demon for optimal control of open quantum systems","created":"2024-08-27","cited_by_count":1,"area":null},{"id":"2506.00398","title":"Position: Olfaction Standardization is Essential for the Advancement of Embodied Artificial Intelligence","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2509.20635","title":"Learning Terrain-Specialized Policies for Adaptive Locomotion in Challenging Environments","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2101.07599","title":"Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments","created":"2021-01-19","cited_by_count":0,"area":null},{"id":"2103.14422","title":"SegVisRL: Visuomotor Development for a Lunar Rover for Hazard Avoidance using Camera Images","created":"2021-03-26","cited_by_count":0,"area":null},{"id":"2107.03741","title":"Adaptation of Quadruped Robot Locomotion with Meta-Learning","created":"2021-07-08","cited_by_count":0,"area":null},{"id":"2110.02332","title":"OTTR: Off-Road Trajectory Tracking using Reinforcement Learning","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2110.08066","title":"Dual-Arm Adversarial Robot Learning","created":"2021-10-15","cited_by_count":0,"area":null},{"id":"2203.00369","title":"Approximating a deep reinforcement learning docking agent using linear model trees","created":"2022-03-01","cited_by_count":0,"area":null},{"id":"2203.13125","title":"Intelligent Systematic Investment Agent: an ensemble of deep learning and evolutionary strategies","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2207.00797","title":"Learning fast and agile quadrupedal locomotion over complex terrain","created":"2022-07-02","cited_by_count":0,"area":null},{"id":"2211.13070","title":"Enhancing team performance with transfer-learning during real-world human-robot collaboration","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2303.02640","title":"Swim: A General-Purpose, High-Performing, and Efficient Activation Function for Locomotion Control Tasks","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2304.10260","title":"Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive Imitation","created":"2023-04-19","cited_by_count":0,"area":null}],"next_cursor":"100"}