mlsanityData to 14 Oct 2026

Relational Mimic for Visual Adversarial Imitation Learning

arXiv 1912.08444 ↗First posted 18 Dec 2019cs.LG cs.AI cs.CVcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

In this work, we introduce a new method for imitation learning from video demonstrations. Our method, Relational Mimic (RM), improves on previous visual imitation learning methods by combining generative adversarial networks and relational learning. RM is flexible and can be used in conjunction with other recent advances in generative adversarial imitation learning to better address the need for more robust and sample-efficient approaches. In addition, we introduce a new neural network architecture that improves upon the previous state-of-the-art in reinforcement learning and illustrate how increasing the relational reasoning capabilities of the agent enables the latter to achieve increasingly higher performance in a challenging locomotion task with pixel inputs. Finally, we study the effects and contributions of relational learning in policy evaluation, policy improvement and reward learning through ablation studies.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 43 of its 74 references that are in the map. First posted on arXiv 18 Dec 2019.

Builds on

43 of 74 references.

Closest ancestors · 5

Same direction, newest first

  1. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep
  2. 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets6 Sep
  3. 2018Risk-Sensitive Generative Adversarial Imitation Learning13 Aug
  4. 2018Generative Adversarial Imitation from Observation17 Jul
  5. 2018Behavioral Cloning from Observation4 May

Other references · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2017Graph Attention Networkscited by 8,923
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2016Layer Normalizationcited by 5,669
  7. 2017Non-local Neural Networkscited by 2,293
  8. 2017Improved Training of Wasserstein GANscited by 2,235
  9. 2016OpenAI Gymcited by 1,736
  10. 2016Concrete Problems in AI Safetycited by 1,642
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  12. 2016Generative Adversarial Imitation Learningcited by 1,597
26 more
  1. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  2. 2016End to End Learning for Self-Driving Carscited by 1,009
  3. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  4. 2018Self-Attention Generative Adversarial Networkscited by 809
  5. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  6. 2017Deep Reinforcement Learning that Matterscited by 754
  7. 2018Learning Dexterous In-Hand Manipulationcited by 687
  8. 2017Wasserstein GANcited by 639
  9. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  10. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 509
  11. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  12. 2019Attention Augmented Convolutional Networkscited by 363
  13. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  14. 2017A simple neural network module for relational reasoningcited by 346
  15. 2018Neural Relational Inference for Interacting Systemscited by 339
  16. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  17. 2017Inverse Reward Designcited by 249
  18. 2017AI Safety Gridworldscited by 110
  19. 2017Learning human behaviors from motion capture by adversarial imitationcited by 77
  20. 2018Synthesizing Programs for Images using Reinforced Adversarial Learningcited by 72
  21. 2017Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Netscited by 64
  22. 2017VAIN: Attentional Multi-agent Predictive Modelingcited by 53
  23. 2016Model-Free Imitation Learning with Policy Optimizationcited by 52
  24. 2017Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Stepcited by 45
  25. 2018A Large-Scale Study on Regularization and Normalization in GANscited by 26
  26. 2019TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensorscited by 17

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021RAIL: A modular framework for Reinforcement-learning-based Adversarial Imitation Learning
  2. 2024Diffusion-Reward Adversarial Imitation Learning
  3. 2023Adversarial Imitation Learning from Visual Observations using Latent Information
  4. 2021Visual Adversarial Imitation Learning using Variational Models
  5. 2026Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies
  6. 2021Domain-Robust Visual Imitation Learning with Mutual Information Constraints
  7. 2022Latent Policies for Adversarial Imitation Learning
  8. 2025SD2AIL: Adversarial Imitation Learning from Synthetic Demonstrations via Diffusion Models