{"total":30,"rows":[{"id":"2401.16889","title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","created":"2024-01-30","cited_by_count":99,"area":"deeprl"},{"id":"2406.20083","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","created":"2024-06-28","cited_by_count":58,"area":"deeprl"},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2512.01996","title":"Learning Sim-to-Real Humanoid Locomotion in 15 Minutes","created":"2025-12-01","cited_by_count":16,"area":"deeprl"},{"id":"2402.09992","title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts","created":"2024-02-15","cited_by_count":6,"area":"deeprl"},{"id":"2410.04553","title":"Bisimulation metric for Model Predictive Control","created":"2024-10-06","cited_by_count":6,"area":"deeprl"},{"id":"2408.00309","title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning","created":"2024-08-01","cited_by_count":4,"area":"deeprl"},{"id":"2403.12210","title":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","created":"2024-03-18","cited_by_count":3,"area":"deeprl"},{"id":"2408.07962","title":"Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning","created":"2024-08-15","cited_by_count":3,"area":"deeprl"},{"id":"2411.01827","title":"Risk-sensitive control as inference with R\\'enyi divergence","created":"2024-11-04","cited_by_count":3,"area":"deeprl"},{"id":"2406.04920","title":"Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning","created":"2024-06-07","cited_by_count":2,"area":"deeprl"},{"id":"2409.09990","title":"SHIRE: Enhancing Sample Efficiency using Human Intuition in REinforcement Learning","created":"2024-09-16","cited_by_count":2,"area":"deeprl"},{"id":"2410.10438","title":"Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives","created":"2024-10-14","cited_by_count":2,"area":"deeprl"},{"id":"2509.06296","title":"Learning to Walk With Less: A Dyna-Style Approach to Quadrupedal Locomotion","created":"2025-09-08","cited_by_count":2,"area":"deeprl"},{"id":"2603.02008","title":"Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards","created":"2026-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2409.08815","title":"Deep reinforcement learning for tracking a moving target in jellyfish-like swimming","created":"2024-09-13","cited_by_count":1,"area":"deeprl"},{"id":"2409.19716","title":"Constrained Reinforcement Learning for Safe Heat Pump Control","created":"2024-09-29","cited_by_count":1,"area":"deeprl"},{"id":"2506.10871","title":"Viability of Future Actions: Robust Safety in Reinforcement Learning via Entropy Regularization","created":"2025-06-12","cited_by_count":1,"area":"deeprl"},{"id":"2506.20036","title":"Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion","created":"2025-06-24","cited_by_count":1,"area":"deeprl"},{"id":"2509.04069","title":"Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning","created":"2025-09-04","cited_by_count":1,"area":"deeprl"},{"id":"2601.21363","title":"Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2606.19357","title":"Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots","created":"2026-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2402.00676","title":"Deep Robot Sketching: An application of Deep Q-Learning Networks for human-like sketching","created":"2024-02-01","cited_by_count":0,"area":"deeprl"},{"id":"2405.00389","title":"Employing Federated Learning for Training Autonomous HVAC Systems","created":"2024-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2501.17801","title":"Consensus Based Stochastic Control","created":"2025-01-29","cited_by_count":0,"area":"deeprl"},{"id":"2503.14554","title":"Synchronous vs Asynchronous Reinforcement Learning in a Real World Robot","created":"2025-03-17","cited_by_count":0,"area":"deeprl"},{"id":"2603.07110","title":"Learning From Failures: Efficient Reinforcement Learning Control with Episodic Memory","created":"2026-03-07","cited_by_count":0,"area":"deeprl"},{"id":"2605.09595","title":"Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain","created":"2026-05-10","cited_by_count":0,"area":"deeprl"},{"id":"2607.08925","title":"SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions","created":"2026-07-09","cited_by_count":0,"area":"deeprl"},{"id":"2607.17897","title":"Distributional Soft Bellman Operator under the Cram\\'er Geometry","created":"2026-07-20","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}