mlsanityData to 7 Oct 2026

Stochastic Action Prediction for Imitation Learning

arXiv 2101.01055 ↗First posted 26 Dec 2020cs.LG cs.ROcited by 0

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

Abstract (arXiv)

Imitation learning is a data-driven approach to acquiring skills that relies on expert demonstrations to learn a policy that maps observations to actions. When performing demonstrations, experts are not always consistent and might accomplish the same task in slightly different ways. In this paper, we demonstrate inherent stochasticity in demonstrations collected for tasks including line following with a remote-controlled car and manipulation tasks including reaching, pushing, and picking and placing an object. We model stochasticity in the data distribution using autoregressive action generation, generative adversarial nets, and variational prediction and compare the performance of these approaches. We find that accounting for stochasticity in the expert data leads to substantial improvement in the success rate of task completion.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 14 of its 21 references that are in the map. First posted on arXiv 26 Dec 2020.

Builds on

14 of 21 references.

References · 14

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2014Conditional Generative Adversarial Netscited by 2,152
  6. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  7. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  8. 2016Pixel Recurrent Neural Networkscited by 814
  9. 2017Wasserstein GANcited by 635
  10. 2019Model-Based Reinforcement Learning for Ataricited by 495
  11. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  12. 2017Stochastic Variational Video Predictioncited by 234
2 more
  1. 2018One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learningcited by 146
  2. 2017Deep Reinforcement Learning for High Precision Assembly Taskscited by 37

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021CRIL: Continual Robot Imitation Learning via Generative and Prediction Model
  2. 2023Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective
  3. 2023Provably Efficient Adversarial Imitation Learning with Unknown Transitions
  4. 2022Latent Policies for Adversarial Imitation Learning
  5. 2022Imitation Learning by Estimating Expertise of Demonstrators
  6. 2023Sample-efficient Adversarial Imitation Learning
  7. 2019Generative predecessor models for sample-efficient imitation learning
  8. 2018Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information