mlsanityData to 7 Oct 2026

A Statistical Guarantee for Representation Transfer in Multitask Imitation Learning

arXiv 2311.01589 ↗First posted 2 Nov 2023cs.LGcited by 1

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

Abstract (arXiv)

Transferring representation for multitask imitation learning has the potential to provide improved sample efficiency on learning new tasks, when compared to learning from scratch. In this work, we provide a statistical guarantee indicating that we can indeed achieve improved sample efficiency on the target task when a representation is trained using sufficiently diverse source tasks. Our theoretical results can be readily extended to account for commonly used neural network architectures with realistic assumptions. We conduct empirical analyses that align with our theoretical findings on four simulated environmentsunicodex2014in particular leveraging more data from source tasks can improve sample efficiency on learning in the new task.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 33 of its 41 references that are in the map. First posted on arXiv 2 Nov 2023.

Builds on

33 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning4 Feb

Other references · 32

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  6. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  8. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  9. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  10. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  11. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  12. 2020dm_control: Software and Tasks for Continuous Controlcited by 368
20 more
  1. 2015Norm-Based Capacity Control in Neural Networkscited by 299
  2. 2017Size-Independent Sample Complexity of Neural Networkscited by 289
  3. 2021Deep learning: a statistical viewpointcited by 239
  4. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 220
  5. 2015The Benefit of Multitask Representation Learningcited by 194
  6. 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
  7. 2020Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPOcited by 184
  8. 2016A vector-contraction inequality for Rademacher complexitiescited by 141
  9. 2020Error Bounds of Imitating Policies and Environmentscited by 90
  10. 2022On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baselinecited by 55
  11. 2020Provable Representation Learning for Imitation Learning via Bi-level Optimizationcited by 41
  12. 2020Revisiting Design Choices in Proximal Policy Optimizationcited by 38
  13. 2021Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policiescited by 37
  14. 2022MAML and ANIL Provably Learn Representationscited by 30
  15. 2022Multi-Task Imitation Learning for Linear Dynamical Systemscited by 22
  16. 2021Continuous Control with Action Quantization from Demonstrationscited by 21
  17. 2022Solving Continuous Control via Q-learningcited by 21
  18. 2022On Rademacher Complexity-based Generalization Bounds for Deep Learningcited by 16
  19. 2022Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Taskscited by 10
  20. 2023Imitation and Transfer Learning for LQG Controlcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrationscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2020Scalable Multi-Task Imitation Learning with Autonomous Improvement
  2. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learning
  3. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
  4. 2022SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning
  5. 2020Complex Skill Acquisition Through Simple Skill Imitation Learning
  6. 2022Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task Division
  7. 2022An Empirical Investigation of Representation Learning for Imitation
  8. 2023Sample-efficient Adversarial Imitation Learning