{"total":77,"rows":[{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511,"area":null},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2103.02142","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","created":"2021-03-03","cited_by_count":77,"area":null},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77,"area":null},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2102.00714","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","created":"2021-02-01","cited_by_count":63,"area":"offlinerl"},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"id":"2210.06463","title":"Holo-Dex: Teaching Dexterity with Immersive Mixed Reality","created":"2022-10-12","cited_by_count":57,"area":null},{"id":"2106.04531","title":"RobustNav: Towards Benchmarking Robustness in Embodied Navigation","created":"2021-06-08","cited_by_count":54,"area":null},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2102.11492","title":"DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning","created":"2021-02-23","cited_by_count":48,"area":"offlinerl"},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38,"area":null},{"id":"2111.02767","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","created":"2021-11-04","cited_by_count":31,"area":"offlinerl"},{"id":"2102.07659","title":"Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems","created":"2021-02-15","cited_by_count":24,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2307.15690","title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","created":"2023-07-28","cited_by_count":23,"area":"offlinerl"},{"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":"2209.12016","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","created":"2022-09-24","cited_by_count":21,"area":null},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2106.00133","title":"AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2511.12120","title":"Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy","created":"2025-11-15","cited_by_count":15,"area":"deeprl"},{"id":"2305.13681","title":"GUARD: A Safe Reinforcement Learning Benchmark","created":"2023-05-23","cited_by_count":13,"area":null},{"id":"2301.12593","title":"Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2111.10247","title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","created":"2021-11-19","cited_by_count":10,"area":null},{"id":"2110.04003","title":"Learning to Centralize Dual-Arm Assembly","created":"2021-10-08","cited_by_count":9,"area":null},{"id":"2301.13375","title":"Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees","created":"2023-01-31","cited_by_count":9,"area":null},{"id":"2306.07818","title":"A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2306.05859","title":"Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2310.08731","title":"Novelty Detection in Reinforcement Learning with World Models","created":"2023-10-12","cited_by_count":8,"area":"wm"},{"id":"2509.18648","title":"SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer","created":"2025-09-23","cited_by_count":8,"area":"deeprl"},{"id":"2010.08353","title":"On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration","created":"2020-10-16","cited_by_count":6,"area":"offlinerl"},{"id":"2204.09424","title":"SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2307.02991","title":"ContainerGym: A Real-World Reinforcement Learning Benchmark for Resource Allocation","created":"2023-07-06","cited_by_count":6,"area":null},{"id":"2311.18736","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","created":"2023-11-30","cited_by_count":6,"area":null},{"id":"2503.08241","title":"HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents","created":"2025-03-11","cited_by_count":6,"area":"deeprl"},{"id":"2601.19612","title":"Safe Exploration via Policy Priors","created":"2026-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2503.01919","title":"Reinforcement learning with combinatorial actions for coupled restless bandits","created":"2025-03-01","cited_by_count":5,"area":"deeprl"},{"id":"2104.14534","title":"On the Emergence of Whole-body Strategies from Humanoid Robot Push-recovery Learning","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2106.03934","title":"Offline Policy Comparison under Limited Historical Agent-Environment Interactions","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2206.03846","title":"Sim2real for Reinforcement Learning Driven Next Generation Networks","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2308.07741","title":"Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World","created":"2023-08-15","cited_by_count":3,"area":"offlinerl"},{"id":"2312.07178","title":"Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2507.00257","title":"Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning","created":"2025-06-30","cited_by_count":3,"area":"deeprl"},{"id":"2101.12501","title":"Learning-based vs Model-free Adaptive Control of a MAV under Wind Gust","created":"2021-01-29","cited_by_count":2,"area":null},{"id":"2110.08307","title":"GrowSpace: Learning How to Shape Plants","created":"2021-10-15","cited_by_count":2,"area":null},{"id":"2112.01575","title":"Towards Interactive Reinforcement Learning with Intrinsic Feedback","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2201.07092","title":"K-nearest Multi-agent Deep Reinforcement Learning for Collaborative Tasks with a Variable Number of Agents","created":"2022-01-18","cited_by_count":2,"area":null},{"id":"2407.14516","title":"RobocupGym: A challenging continuous control benchmark in Robocup","created":"2024-07-03","cited_by_count":2,"area":"deeprl"},{"id":"2505.21236","title":"Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies","created":"2025-05-27","cited_by_count":2,"area":"deeprl"},{"id":"2602.24235","title":"SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems","created":"2026-02-27","cited_by_count":2,"area":null},{"id":"2110.09712","title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2304.02480","title":"Quantum Imitation Learning","created":"2023-04-04","cited_by_count":1,"area":"offlinerl"},{"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":"2407.13006","title":"Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2407.15820","title":"On shallow planning under partial observability","created":"2024-07-22","cited_by_count":1,"area":"deeprl"},{"id":"2504.16020","title":"AlphaGrad: Non-Linear Gradient Normalization Optimizer","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2605.28287","title":"AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learning","created":"2026-05-27","cited_by_count":1,"area":"deeprl"},{"id":"2606.12890","title":"Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer","created":"2026-06-11","cited_by_count":1,"area":"deeprl"},{"id":"2108.01789","title":"Monte Carlo Tree Search for high precision manufacturing","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2405.02598","title":"UDUC: An Uncertainty-driven Approach for Learning-based Robust Control","created":"2024-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2406.14214","title":"REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2410.02789","title":"Logic-Free Building Automation: Learning the Control of Room Facilities with Wall Switches and Ceiling Camera","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2410.08979","title":"Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control","created":"2024-10-11","cited_by_count":0,"area":"deeprl"},{"id":"2411.01342","title":"Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity","created":"2024-11-02","cited_by_count":0,"area":"wm"},{"id":"2510.07635","title":"Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2602.02530","title":"Formulating Reinforcement Learning for Human-Robot Collaboration through Off-Policy Evaluation","created":"2026-01-27","cited_by_count":0,"area":"offlinerl"},{"id":"2602.18856","title":"Issues with Measuring Task Complexity via Random Policies in Robotic Tasks","created":"2026-02-21","cited_by_count":0,"area":"deeprl"},{"id":"2605.19469","title":"Sampling-Based Safe Reinforcement Learning","created":"2026-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2607.19628","title":"HypEMBER: Hypernetwork-based Ensemble for Robust Policy Learning of Parametrized Dynamical Systems","created":"2026-07-21","cited_by_count":0,"area":"deeprl"},{"id":"2609.06061","title":"SCoCaT: Success Conditioned Constrained Reinforcement Learning for Spacecraft Docking","created":"2026-09-05","cited_by_count":0,"area":"deeprl"},{"id":"2609.18167","title":"Characterizing Replay Retention Under Dynamics Shift in Model-Based Reinforcement Learning","created":"2026-09-16","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}