mlsanityData to 14 Oct 2026

RL for robot locomotion and manipulation

928 papers7 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: reinforcement, reinforcement learning, robot, policy, manipulation

Key facts. RL for robot locomotion and manipulation: 928 papers on arXiv since 2024 (data through 14 Oct 2026). 60 of its 928 mapped papers (6%) cite “Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning” (2024, arXiv 2410.21845). 35 new papers 30 Sep–14 Oct.

What’s new

30 Sep – 14 Oct 2026

35 new papers, 30 Sep – 14 Oct; 7 this week.

  1. This week · 7
  2. Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion
  3. Hyperspherical Contrastive Representations Unlock Planning and Exploration also fits: RL for robot navigation and UAV control
  4. ACRO: Actor-Critic Rollout Orchestration also fits: Interpretable and logic-guided RL
  5. Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning
  6. PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation
  7. VLRLA: Deployment-Time Adaptation of Vision-Language-Action Models through In-Context Reinforcement Learning also fits: Deep RL algorithms and representations
  8. OneDemo: Unified Policy Learning and Data Generation from a Single Demonstration
  9. Earlier · 28
  10. P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning
  11. Chunk-wise Model-based Policy Optimization
  12. From Video to Vision: Learning Generalizable Humanoid Carrying from Human Motion
All 35
  1. Learning to See through Action: Predictive Curiosity for Robots
  2. Disentangling Task-Relevant Latent Dynamics for Reward Modeling
  3. Evo-RL: Iterative Robot Reinforcement Learning from Selective Experience
  4. OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
  5. Leveraging Human-In-The-Loop Demonstrations in Reinforcement Learning for Digital Twin-Driven Robot Flexibility
  6. A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning
  7. Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation
  8. NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime also fits: Interpretable and logic-guided RL
  9. Energy-Efficient Gait Adaptation via Hierarchical Reinforcement Learning for Quadrupedal Locomotion Across Diverse Terrains
  10. A Scoping Review and Experimental Study on Reinforcement Learning from Human Feedback for Human-Robot Collaboration
  11. Teaching a Robot Dog New Tricks: Diverse Quadruped Skills via Combined Reinforcement and Imitation Learning with Adversarial Task Selection
  12. HULK: Learning Whole-Body Forceful Loco-Manipulation for Humanoids
  13. QF3: Fast Flow RL with Filtered Q-Gradients also fits: RL with diffusion and flow models
  14. Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents
  15. BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation
  16. Task-Space Imitation Guidance for Efficient Reinforcement Learning
  17. I-BFM: Reward-Conditioned Robust Humanoid Interaction via Unsupervised Reinforcement Learning
  18. Hierarchical Reinforcement Learning for Collision-Free Locomotion of an Underactuated Biped
  19. PatternDex: Learning Interaction Patterns to Guide Reinforcement Learning of Bimanual Dexterous Manipulation of Articulated Objects
  20. Reinforcement Learning from Real-Robot Interaction without High-Quality State Estimates
  21. Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos also fits: Deep RL algorithms and representations
  22. PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots
  23. Tactile Curiosity Drives Robot Interaction
  24. PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning also fits: Deep RL algorithms and representations
  25. Locomotion-Grounded Humanoid Soccer: Task-Gated Reinforcement Learning of a Multi-Directional Kicking Library

Foundations

Most cited by papers here

  1. Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning2024cited by 60 here
  2. Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control2024cited by 46 here
  3. SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning2024cited by 42 here
  4. Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation2024cited by 24 here
  5. Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes2024cited by 23 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learningcited by 42 here
  2. 2024Diffusion Policy Policy Optimizationcited by 25 here
  3. 2025Steering Your Diffusion Policy with Latent Space Reinforcement Learningcited by 22 here
  4. 2025RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learningcited by 17 here
  5. 2026RL Token: Bootstrapping Online RL with Vision-Language-Action Modelscited by 13 here
19 more it builds on, not in this chain
  1. 2024Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Designcited by 11 here
  2. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 46 here
  3. 2024Learning Human-to-Humanoid Real-Time Whole-Body Teleoperationcited by 24 here
  4. 2024Leveraging Symmetry in RL-based Legged Locomotion Controlcited by 11 here
  5. 2024CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learningcited by 10 here
  6. 2024CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotioncited by 14 here
  7. 2024Gymnasium: A Standard Interface for Reinforcement Learning Environmentscited by 19 here
  8. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 23 here
  9. 2024Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learningcited by 21 here
  10. 2024One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotioncited by 14 here
  11. 2024SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learningcited by 12 here
  12. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learningcited by 60 here
  13. 2024RLDG: Robotic Generalist Policy Distillation via Reinforcement Learningcited by 15 here
  14. 2025Improving Vision-Language-Action Model with Online Reinforcement Learningcited by 18 here
  15. 2025Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoidscited by 12 here
  16. 2025ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learningcited by 14 here
  17. 2025RSL-RL: A Learning Library for Robotics Researchcited by 12 here
  18. 2025A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learningcited by 11 here
  19. 2025OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interactioncited by 14 here

The 24 most cited of 599.

Browse

30 of 928, ranked 6–35

  1. 6Steering Your Diffusion Policy with Latent Space Reinforcement Learning202522
  2. 7Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning202421
  3. 8Gymnasium: A Standard Interface for Reinforcement Learning Environments202419
  4. 9Improving Vision-Language-Action Model with Online Reinforcement Learning202518
  5. 10RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning202517
  6. 11RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning202415
  7. 12OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction202514
  8. 13CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion202414
  9. 14One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion202414
  10. 15RL Token: Bootstrapping Online RL with Vision-Language-Action Models202613
All 30
  1. 16Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids202512
  2. 17RSL-RL: A Learning Library for Robotics Research202512
  3. 18A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning202511
  4. 19Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design202411
  5. 20Leveraging Symmetry in RL-based Legged Locomotion Control202411
  6. 21CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning202410
  7. 22Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning202410
  8. 23FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control20259
  9. 24Rank2Reward: Learning Shaped Reward Functions from Passive Video20248
  10. 25PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers20257
  11. 26A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards20247
  12. 27FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning20247
  13. 28Learning Sim-to-Real Humanoid Locomotion in 15 Minutes20256
  14. 29Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learning20246
  15. 30Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers20246
  16. 31A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning20246
  17. 32Integrating Model-Based Footstep Planning with Model-Free Reinforcement Learning for Dynamic Legged Locomotion20246
  18. 33DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots20246
  19. 34SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience20246
  20. 35Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies20246