mlsanityData to 14 Oct 2026

RSL-RL: A Learning Library for Robotics Research

arXiv 2509.10771 ↗First posted 13 Sep 2025cs.RO cs.LGcited by 49

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

RSL-RL is an open-source Reinforcement Learning library tailored to the specific needs of the robotics community. Unlike broad general-purpose frameworks, its design philosophy prioritizes a compact and easily modifiable codebase, allowing researchers to adapt and extend algorithms with minimal overhead. The library focuses on algorithms most widely adopted in robotics, together with auxiliary techniques that address robotics-specific challenges. Optimized for GPU-only training, RSL-RL achieves high-throughput performance in large-scale simulation environments. Its effectiveness has been validated in both simulation benchmarks and in real-world robotic experiments, demonstrating its utility as a lightweight, extensible, and practical framework to develop learning-based robotic controllers. The library is open-sourced at: https://github.com/leggedrobotics/rsl_rl.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 28 of its 38 references that are in the map. First posted on arXiv 13 Sep 2025.

Builds on

28 of 38 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning3 Feb
  2. 2024Guided Reinforcement Learning for Robust Multi-Contact Loco-Manipulation17 Oct
  3. 2024CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning27 Mar

Other references · 25

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2018Exploration by Random Network Distillationcited by 993
  4. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 664
  5. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  6. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  7. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
  8. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
  9. 2023Extreme Parkour with Legged Robotscited by 164
  10. 2023ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robotscited by 152
  11. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 138
  12. 2022Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotioncited by 121
13 more
  1. 2024HOVER: Versatile Neural Whole-Body Controller for Humanoid Robotscited by 91
  2. 2025MuJoCo Playgroundcited by 78
  3. 2022Penalized Proximal Policy Optimization for Safe Reinforcement Learningcited by 68
  4. 2024WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contactscited by 61
  5. 2022skrl: Modular and Flexible Library for Reinforcement Learningcited by 49
  6. 2024Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robotscited by 48
  7. 2025Attention-Based Map Encoding for Learning Generalized Legged Locomotioncited by 40
  8. 2022Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learningcited by 37
  9. 2024Symmetry Considerations for Learning Task Symmetric Robot Policiescited by 28
  10. 2024Pedipulate: Enabling Manipulation Skills using a Quadruped Robot's Legcited by 27
  11. 2025Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuningcited by 26
  12. 2023Learning Agile Locomotion on Risky Terrainscited by 21
  13. 2024MARLadona -- Towards Cooperative Team Play Using Multi-Agent Reinforcement Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 41.

49 papers.

Sort:

By area:

  1. 2025Learning Sim-to-Real Humanoid Locomotion in 15 Minutescited by 16
  2. 2026Flow Policy Gradients for Robot Controlcited by 16
  3. 2025Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfercited by 15
  4. 2025SoftMimic: Learning Compliant Whole-body Control from Examplescited by 14
  5. 2026FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructionscited by 10
  6. 2025From Generated Human Videos to Physically Plausible Robot Trajectoriescited by 6
  7. 2025Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolutioncited by 5
  8. 2026PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learningcited by 5
  9. 2026FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Controlcited by 5
  10. 2026Scaling Rough Terrain Locomotion with Automatic Curriculum Reinforcement Learningcited by 3
  11. 2026SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flowscited by 3
  12. 2026PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeballcited by 3
37 more
  1. 2025PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representationscited by 2
  2. 2026ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientationcited by 2
  3. 2026HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teacherscited by 2
  4. 2026Trust-Region Diffusion Policies for Massively Parallel On-Policy RLcited by 2
  5. 2026WaveLander: A Generalizable Hierarchical Control Framework for UAV Landing on Wave-Disturbed Platforms via Reinforcement Learningcited by 2
  6. 2025End-to-End Crop Row Navigation via LiDAR-Based Deep Reinforcement Learningcited by 1
  7. 2026Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Controlcited by 1
  8. 2026Learning Policy Representations for Steerable Behavior Synthesiscited by 1
  9. 2026NFPO: Stabilized Policy Optimization of Normalizing Flow for Robotic Policy Learningcited by 1
  10. 2026Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradientcited by 1
  11. 2026When Is a Learned Command Adapter Worth It? Closed-Loop Identification and Counterfactual Auditing of Frozen Locomotion Policiescited by 1
  12. 2025Pretraining in Actor-Critic Reinforcement Learning for Locomotioncited by 0
  13. 2026Learning End-to-End Control for Omnidirectional Aerial Motion on Overactuated Tilt-rotor Quadrotorscited by 0
  14. 2026Path-conditioned Reinforcement Learning-based Local Planning for Long-Range Navigationcited by 0
  15. 2026PriPG-RL: Privileged Planner-Guided Reinforcement Learning for Partially Observable Systems with Anytime-Feasible MPCcited by 0
  16. 2026Bounded Ratio Reinforcement Learningcited by 0
  17. 2026Hidden States as Value Gradients: The Pontryagin Structure of Recurrent Policiescited by 0
  18. 2026Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomycited by 0
  19. 2026Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotioncited by 0
  20. 2026Beyond Binary: Sim-to-Real Dexterous Manipulation with Physics-Grounded Contact Representationcited by 0
  21. 2026Redesigning Regularization for Effective Policy Smoothingcited by 0
  22. 2026Kine2Go: Kinematic dataset for the Unitree Go2 robot with diverse gaits and motionscited by 0
  23. 2026Agile Fall Recovery for Quadrotors with Bidirectional Thrust via Reinforcement Learningcited by 0
  24. 2026CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotioncited by 0
  25. 2026Rotation-Aware Point-Cloud Embeddings for Vision-Based In-Hand Reorientationcited by 0
  26. 2026PPO-EAL: Exact Augmented Lagrangian Proximal Policy Optimization for Safe Robotic Controlcited by 0
  27. 2026Adaptive Undulatory Locomotion of Snake-like Robots in Dynamic Viscous Environments via Deep Reinforcement Learningcited by 0
  28. 2026Learning Adaptive Multi-Task Guidance, Navigation, and Control via Hypernetworkscited by 0
  29. 2026Open-DiffLoco: Open-Source Differentiable Learning for Deployable Blind Quadruped Locomotioncited by 0
  30. 2026Actuator Dynamics Curricula for Narrow-Viability Tasks in Legged Robot Learningcited by 0
  31. 2026Size Doesn't Matter: Material-State Reinforcement Learning for Excavator Transferable Soil Manipulationcited by 0
  32. 2026Grasp2Twist: Learning Bimanual Dexterous Jar Opening by Reinforcement Learningcited by 0
  33. 2026Predictive Safety Curricula for Robust Legged Locomotioncited by 0
  34. 2026Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learningcited by 0
  35. 2026Bidirectional Voronoi-biased Exploration Curriculum for Reinforcement Learningcited by 0
  36. 2026Optimal Control with Learned Critics under Unmodeled State Dependenciescited by 0
  37. 2026GLST: Global-Local Spatio-Temporal Memory Decomposition Framework for Online Chained-Goal Navigationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
  2. 2026RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control
  3. 2025Taxonomy and Trends in Reinforcement Learning for Robotics and Control Systems: A Structured Review
  4. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes
  5. 2025Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots
  6. 2024Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research
  7. 2024Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer
  8. 2024Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning