mlsanityData to 7 Oct 2026

Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations

arXiv 2206.11693 ↗First posted 23 Jun 2022cs.RO cs.AI cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Learning agile skills is one of the main challenges in robotics. To this end, reinforcement learning approaches have achieved impressive results. These methods require explicit task information in terms of a reward function or an expert that can be queried in simulation to provide a target control output, which limits their applicability. In this work, we propose a generative adversarial method for inferring reward functions from partial and potentially physically incompatible demonstrations for successful skill acquirement where reference or expert demonstrations are not easily accessible. Moreover, we show that by using a Wasserstein GAN formulation and transitions from demonstrations with rough and partial information as input, we are able to extract policies that are robust and capable of imitating demonstrated behaviors. Finally, the obtained skills such as a backflip are tested on an agile quadruped robot called Solo 8 and present faithful replication of hand-held human demonstrations.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 25 of its 50 references that are in the map. First posted on arXiv 23 Jun 2022.

Builds on

25 of 50 references.

References · 25

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2016Generative Adversarial Imitation Learningcited by 1,576
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  5. 2016Least Squares Generative Adversarial Networkscited by 1,000
  6. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  7. 2017Wasserstein GANcited by 635
  8. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  9. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  10. 2018Behavioral Cloning from Observationcited by 482
  11. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  12. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
13 more
  1. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  2. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  3. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 299
  4. 2019Self-Supervised Exploration via Disagreementcited by 263
  5. 2019Provably Efficient Exploration in Policy Optimizationcited by 203
  6. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 191
  7. 2017Robust Imitation of Diverse Behaviorscited by 85
  8. 2017Learning human behaviors from motion capture by adversarial imitationcited by 75
  9. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 68
  10. 2022Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learningcited by 23
  11. 2019An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Researchcited by 18
  12. 2021AMP: Adversarial Motion Priors for Stylized Physics-Based Character Controlcited by 18
  13. 2020Augmenting GAIL with BC for sample efficient imitation learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 9; 2025: 9; 2026: 3.

30 papers.

Sort:

By area:

  1. 2023Robot Parkour Learningcited by 115
  2. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
  3. 2024Visual Whole-Body Control for Legged Loco-Manipulationcited by 58
  4. 2025Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Roboticscited by 47
  5. 2023Prompt a Robot to Walk with Large Language Modelscited by 44
  6. 2023Generalized Animal Imitator: Agile Locomotion with Versatile Motion Priorcited by 17
  7. 2024FLD: Fourier Latent Dynamics for Structured Motion Representation and Learningcited by 14
  8. 2022Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motionscited by 13
  9. 2024Causal Action Influence Aware Counterfactual Data Augmentationcited by 12
  10. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasetscited by 10
  11. 2024SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experiencecited by 10
  12. 2024Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllerscited by 9
18 more
  1. 2023Learning Diverse Skills for Local Navigation under Multi-constraint Optimalitycited by 7
  2. 2023Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Rewardcited by 5
  3. 2023Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Modelscited by 5
  4. 2025High-Performance Reinforcement Learning on Spot: Optimizing Simulation Parameters with Distributional Measurescited by 5
  5. 2025Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Controlcited by 5
  6. 2025Unsupervised Skill Discovery as Exploration for Learning Agile Locomotioncited by 5
  7. 2024Zero-Shot Offline Imitation Learning via Optimal Transportcited by 3
  8. 2025Symmetry-Guided Memory Augmentation for Efficient Locomotion Learningcited by 3
  9. 2026InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skillscited by 3
  10. 2023DeepTransition: Viability Leads to the Emergence of Gait Transitions in Learning Anticipatory Quadrupedal Locomotion Skillscited by 2
  11. 2025Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraintscited by 2
  12. 2025Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged Robotscited by 2
  13. 2025Feature-Based vs. GAN-Based Learning from Demonstrations: When and Whycited by 1
  14. 2026Constraint-Aware Diffusion Priors for High-Fidelity and Versatile Quadruped Locomotioncited by 1
  15. 2024Integrating Controllable Motion Skills from Demonstrationscited by 0
  16. 2024Reinforcement Learning from Wild Animal Videoscited by 0
  17. 2025Dino-Diffusion Modular Designs Bridge the Cross-Domain Gap in Autonomous Parkingcited by 0
  18. 2026LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stuntscited by 0