mlsanityData to 7 Oct 2026

Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior

arXiv 2212.03238 ↗First posted 6 Dec 2022cs.RO cs.AI cs.LGcited by 113

Not on the map. Why?

Abstract (arXiv)

Learned locomotion policies can rapidly adapt to diverse environments similar to those experienced during training but lack a mechanism for fast tuning when they fail in an out-of-distribution test environment. This necessitates a slow and iterative cycle of reward and environment redesign to achieve good performance on a new task. As an alternative, we propose learning a single policy that encodes a structured family of locomotion strategies that solve training tasks in different ways, resulting in Multiplicity of Behavior (MoB). Different strategies generalize differently and can be chosen in real-time for new tasks or environments, bypassing the need for time-consuming retraining. We release a fast, robust open-source MoB locomotion controller, Walk These Ways, that can execute diverse gaits with variable footswing, posture, and speed, unlocking diverse downstream tasks: crouching, hopping, high-speed running, stair traversal, bracing against shoves, rhythmic dance, and more. Video and code release: https://gmargo11.github.io/walk-these-ways/

Key facts. Cited by 113 papers in the map (data through 7 Oct 2026). Builds on 24 of its 29 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

24 of 29 references.

References · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  3. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  4. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  5. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  6. 2015Illuminating search spaces by mapping elitescited by 406
  7. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  8. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  9. 2014Robots that can adapt like animalscited by 203
  10. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  11. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 95
  12. 2020One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RLcited by 79
12 more
  1. 2020Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Compositioncited by 71
  2. 2021Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robotscited by 67
  3. 2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 61
  4. 2021Fast and Efficient Locomotion via Learned Gait Transitionscited by 50
  5. 2019Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Controlcited by 43
  6. 2021Learning to Jump from Pixelscited by 39
  7. 2022Redeeming Intrinsic Rewards via Constrained Optimizationcited by 24
  8. 2022Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controllercited by 23
  9. 2022Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learningcited by 23
  10. 2021Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoirescited by 20
  11. 2021Learning a subspace of policies for online adaptation in Reinforcement Learningcited by 14
  12. 2022Sim-to-Real Learning of Footstep-Constrained Bipedal Dynamic Walkingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 19; 2024: 33; 2025: 39; 2026: 22.

113 papers.

Sort:

By area:

  1. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 153
  2. 2025Time-R1: Post-Training Large Vision Language Model for Temporal Video Groundingcited by 138
  3. 2025BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusioncited by 128
  4. 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 111
  5. 2024DrEureka: Language Model Guided Sim-To-Real Transfercited by 78
  6. 2025HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpitcited by 65
  7. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 63
  8. 2024Visual Whole-Body Control for Legged Loco-Manipulationcited by 58
  9. 2023QUAR-VLA: Vision-Language-Action Model for Quadruped Robotscited by 55
  10. 2025AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Controlcited by 47
  11. 2024Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Controlcited by 41
  12. 2023Dexterous Functional Graspingcited by 36
38 more
  1. 2024One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotioncited by 34
  2. 2023DribbleBot: Dynamic Legged Manipulation in the Wildcited by 33
  3. 2025BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholdscited by 32
  4. 2023Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Responsecited by 31
  5. 2024GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robotcited by 28
  6. 2025RSL-RL: A Learning Library for Robotics Researchcited by 28
  7. 2023Robust and Versatile Bipedal Jumping Control through Reinforcement Learningcited by 27
  8. 2025MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Modelscited by 27
  9. 2023Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimizationcited by 23
  10. 2024Learning Force Control for Legged Manipulationcited by 19
  11. 2023AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfercited by 17
  12. 2024Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Modelscited by 15
  13. 2023RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotioncited by 14
  14. 2025LocoFormer: Generalist Locomotion via Long-context Adaptationcited by 14
  15. 2024Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Criticscited by 13
  16. 2024Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusioncited by 12
  17. 2024RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewardscited by 12
  18. 2025Towards Embodiment Scaling Laws in Robot Locomotioncited by 12
  19. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  20. 2024Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approachcited by 10
  21. 2025A Unified and General Humanoid Whole-Body Controller for Versatile Locomotioncited by 10
  22. 2024Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushingcited by 9
  23. 2023Learning to See Physical Properties with Active Sensing Motor Policiescited by 7
  24. 2024Robust Robot Walker: Learning Agile Locomotion over Tiny Trapscited by 7
  25. 2024Preference Aligned Diffusion Planner for Quadrupedal Locomotion Controlcited by 7
  26. 2025Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learningcited by 7
  27. 2025SoftMimic: Learning Compliant Whole-body Control from Examplescited by 7
  28. 2023DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policiescited by 6
  29. 2024Automatic Environment Shaping is the Next Frontier in RLcited by 6
  30. 2024PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotioncited by 6
  31. 2024ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimizationcited by 6
  32. 2023Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drivecited by 5
  33. 2023Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theorycited by 5
  34. 2024Versatile Navigation under Partial Observability via Value-guided Diffusion Policycited by 5
  35. 2024Whole-body End-Effector Pose Trackingcited by 5
  36. 2025Ego-Vision World Model for Humanoid Contact Planningcited by 5
  37. 2023Fully Spiking Neural Network for Legged Robotscited by 4
  38. 2024Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learningcited by 4

50 most cited of 113 All 113 (JSON)