mlsanityData to 7 Oct 2026

Towards Improving Learning from Demonstration Algorithms via MCMC Methods

arXiv 2405.02243 ↗First posted 3 May 2024cs.ROcited by 0

On the map: Offline RL and imitation learning from data → Robot learning from demonstration

Abstract (arXiv)

Behavioral cloning, or more broadly, learning from demonstrations (LfD) is a priomising direction for robot policy learning in complex scenarios. Albeit being straightforward to implement and data-efficient, behavioral cloning has its own drawbacks, limiting its efficacy in real robot setups. In this work, we take one step towards improving learning from demonstration algorithms by leveraging implicit energy-based policy models. Results suggest that in selected complex robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly used neural network-based explicit models, especially in the cases of approximating potentially discontinuous and multimodal functions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data. Builds on 37 of its 54 references that are in the map. First posted on arXiv 3 May 2024.

Builds on

37 of 54 references.

References · 37

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  5. 2016Generative Adversarial Imitation Learningcited by 1,576
  6. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  7. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  8. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  9. 2021Implicit Behavioral Cloningcited by 442
  10. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  11. 2021How to Train Your Energy-Based Modelscited by 271
  12. 2019DiffTaichi: Differentiable Programming for Physical Simulationcited by 248
25 more
  1. 2021Offline Reinforcement Learning with Fisher Divergence Critic Regularizationcited by 237
  2. 2018Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluidscited by 219
  3. 2020SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulationcited by 118
  4. 2019Self-Supervised Correspondence in Visuomotor Policy Learningcited by 106
  5. 2021PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physicscited by 100
  6. 2020Residual Energy-Based Models for Text Generationcited by 95
  7. 2022FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objectscited by 91
  8. 2021DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cuttingcited by 62
  9. 2021Learning Visible Connectivity Dynamics for Cloth Smoothingcited by 61
  10. 2022TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulationcited by 47
  11. 2019Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entitiescited by 41
  12. 2020VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulationcited by 40
  13. 2021On the Sample Complexity of Stability Constrained Imitation Learningcited by 38
  14. 2021Planar Robot Casting with Real2Sim2Real Self-Supervised Learningcited by 38
  15. 2021Provable Representation Learning for Imitation with Contrastive Fourier Featurescited by 34
  16. 2023FlowBot++: Learning Generalized Articulated Objects Manipulation via Articulation Projectioncited by 34
  17. 2023DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classificationcited by 23
  18. 2020Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cablescited by 21
  19. 2021Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transformscited by 17
  20. 20206-DoF Grasp Planning using Fast 3D Reconstruction and Grasp Quality CNNcited by 13
  21. 2022ART/ATK: A research platform for assessing and mitigating the sim-to-real gap in robotics and autonomous vehicle engineeringcited by 10
  22. 2023APLA: Additional Perturbation for Latent Noise with Adversarial Training Enables Consistencycited by 9
  23. 2024Multi-Model 3D Registration: Finding Multiple Moving Objects in Cluttered Point Cloudscited by 7
  24. 2021Deformable Elasto-Plastic Object Shaping using an Elastic Hand and Model-Based Reinforcement Learningcited by 6
  25. 2024GMKF: Generalized Moment Kalman Filter for Polynomial Systems with Arbitrary Noisecited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach
  2. 2026Feasibility-aware Imitation Learning from Observation with Multimodal Feedback
  3. 2024Learning from Demonstration Framework for Multi-Robot Systems Using Interaction Keypoints and Soft Actor-Critic Methods
  4. 2020Concurrent Training Improves the Performance of Behavioral Cloning from Observation
  5. 2020Learning from Suboptimal Demonstration via Self-Supervised Reward Regression
  6. 2021Learning from Imperfect Demonstrations from Agents with Varying Dynamics
  7. 2022Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations
  8. 2023A Survey of Demonstration Learning