mlsanityData to 7 Oct 2026

ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills

arXiv 2005.04323 ↗First posted 9 May 2020cs.GR cs.LG cs.ROcited by 44

Not on the map. Why?

Abstract (arXiv)

Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where the footstep locations are fully constrained. Finding good solutions to stepping-stone locomotion is a longstanding and fundamental challenge for animation and robotics. We present fully learned solutions to this difficult problem using reinforcement learning. We demonstrate the importance of a curriculum for efficient learning and evaluate four possible curriculum choices compared to a non-curriculum baseline. Results are presented for a simulated human character, a realistic bipedal robot simulation and a monster character, in each case producing robust, plausible motions for challenging stepping stone sequences and terrains.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 10; 2023: 12; 2024: 4; 2025: 5; 2026: 2.

44 papers.

Sort:

By area:

  1. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  2. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 131
  3. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  4. 2023Neural Volumetric Memory for Visual Locomotion Controlcited by 40
  5. 2021Learning to Jump from Pixelscited by 39
  6. 2023Neural Categorical Priors for Physics-Based Character Controlcited by 37
  7. 2023DTC: Deep Tracking Controlcited by 37
  8. 2023Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotioncited by 33
  9. 2022Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capturecited by 31
  10. 2023Composite Motion Learning with Task Controlcited by 26
  11. 2023Learning and Adapting Agile Locomotion Skills by Transferring Experiencecited by 25
  12. 2022Style-ERD: Responsive and Coherent Online Motion Style Transfercited by 17
32 more
  1. 2024SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillationcited by 16
  2. 2021Discovering Diverse Athletic Jumping Strategiescited by 15
  3. 2023AdaptNet: Policy Adaptation for Physics-Based Character Controlcited by 15
  4. 2021A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Controlcited by 12
  5. 2022A Survey on Reinforcement Learning Methods in Character Animationcited by 12
  6. 2022Learning to Get Upcited by 11
  7. 2022Learning to Brachiate via Simplified Model Imitationcited by 7
  8. 2024FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Modelscited by 6
  9. 2025Learning to Ball: Composing Policies for Long-Horizon Basketball Movescited by 6
  10. 2022Learning Bipedal Walking On Planned Footsteps For Humanoid Robotscited by 5
  11. 2023Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drivecited by 5
  12. 2023Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculumcited by 5
  13. 2024Whole-body End-Effector Pose Trackingcited by 5
  14. 2021Efficient Hyperparameter Optimization for Physics-based Character Animationcited by 4
  15. 2021Control of rough terrain vehicles using deep reinforcement learningcited by 4
  16. 2021Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Plannercited by 4
  17. 2021Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Controlcited by 3
  18. 2021Learning Setup Policies: Reliable Transition Between Locomotion Behaviourscited by 2
  19. 2021Quadruped Locomotion on Non-Rigid Terrain using Reinforcement Learningcited by 2
  20. 2022Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learningcited by 2
  21. 2023MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characterscited by 2
  22. 2025Diffusion-based Planning with Learned Viability Filterscited by 2
  23. 2021Learning Linear Policies for Robust Bipedal Locomotion on Terrains with Varying Slopescited by 1
  24. 2022Learning to Guide Multiple Heterogeneous Actors from a Single Human Demonstration via Automatic Curriculum Learning in StarCraft IIcited by 1
  25. 2023Characterization of Human Balance through a Reinforcement Learning-based Muscle Controllercited by 1
  26. 2024PlaMo: Plan and Move in Rich 3D Physical Environmentscited by 1
  27. 2025Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotioncited by 1
  28. 2025RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characterscited by 1
  29. 2026Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terraincited by 1
  30. 2023Adaptive Tracking of a Single-Rigid-Body Character in Various Environmentscited by 0
  31. 2025HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mambacited by 0
  32. 2026Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Trackingcited by 0