mlsanityData to 14 Oct 2026

Zero-Shot Transfer in Imitation Learning

arXiv 2310.06710 ↗First posted 10 Oct 2023cs.LGcited by 0

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

Abstract (arXiv)

We present an algorithm that learns to imitate expert behavior and can transfer to previously unseen domains without retraining. Such an algorithm is extremely relevant in real-world applications such as robotic learning because 1) reward functions are difficult to design, 2) learned policies from one domain are difficult to deploy in another domain and 3) learning directly in the real world is either expensive or unfeasible due to security concerns. To overcome these constraints, we combine recent advances in Deep RL by using an AnnealedVAE to learn a disentangled state representation and imitate an expert by learning a single Q-function which avoids adversarial training. We demonstrate the effectiveness of our method in 3 environments ranging in difficulty and the type of transfer knowledge required.

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 16 of its 32 references that are in the map. First posted on arXiv 10 Oct 2023.

Builds on

16 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021IQ-Learn: Inverse soft-Q Learning for Imitation23 Jun

Other references · 15

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2016Generative Adversarial Imitation Learningcited by 1,597
  5. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  6. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  7. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  8. 2018Understanding disentangling in β-VAEcited by 335
  9. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 149
  10. 2015Deep Convolutional Inverse Graphics Networkcited by 121
  11. 2020Visual Imitation Made Easycited by 111
  12. 2016Towards Deep Symbolic Reinforcement Learningcited by 42
3 more
  1. 2021Domain Adaptation In Reinforcement Learning Via Latent Unified State Representationcited by 35
  2. 2014Transformation Properties of Learned Visual Representationscited by 18
  3. 2016Generalizing Skills with Semi-Supervised Reinforcement Learningcited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2018Zero-Shot Visual Imitation
  2. 2022Robust Learning from Observation with Model Misspecification
  3. 2024Zero-Shot Offline Imitation Learning via Optimal Transport
  4. 2020State-only Imitation with Transition Dynamics Mismatch
  5. 2025Consistent Zero-Shot Imitation with Contrastive Goal Inference
  6. 2019SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards
  7. 2023Provably Efficient Adversarial Imitation Learning with Unknown Transitions
  8. 2019Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation