Using Task Features for Zero-Shot Knowledge Transfer in Lifelong Learning

@inproceedings{Isele2016UsingTF,
  title={Using Task Features for Zero-Shot Knowledge Transfer in Lifelong Learning},
  author={David Isele and Mohammad Rostami and Eric Eaton},
  booktitle={IJCAI},
  year={2016}
}
Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong learning settings where the goal is to learn each consecutive task rapidly from as little data as possible. To reduce this burden, we develop a lifelong reinforcement learning… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 39 CITATIONS

A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

An Optimization Framework for Task Sequencing in Curriculum Learning

  • 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND

Forward and Backward Knowledge Transfer for Sentiment Classification

Hao Wang, Bing Liu, Shuai Wang, Nianzu Ma, Yan Yang
  • ArXiv
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND

Lifelong Learning for Heterogeneous Multi-Modal Tasks

Huaping Liu, Fuchun Sun, Bin Fang
  • 2019 International Conference on Robotics and Automation (ICRA)
  • 2019
VIEW 2 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES

Paul Ruvolo

Haitham Bou Ammar, Eric Eaton, Jose Marcio Luna
  • Autonomous cross-domain knowledge transfer in lifelong policy gradient reinforcement learning. International Joint Conference on Artificial Intelligence,
  • 2015
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Yi Ma

Jianchao Yang, John Wright, Thomas Huang
  • Image super-resolution via sparse representation. IEEE Transactions on Image Processing, 19(11):2861–2873,
  • 2010
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Machine Learning

Rich Caruana. Multitask Learning
  • 28:41–75,
  • 1997
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Peter Stone

Jivko Sinapov, Sanmit Narvekar, Matteo Leonetti
  • Learning inter-task transferability in the absence of target task samples. International Conference on Autonomous Agents and Multiagent Systems,
  • 2015

Christopher Manning

Jeffrey Pennington, Richard Socher
  • GloVe: Global vectors for word representation. Empiricial Methods in Natural Language Processing, 12:1532–1543,
  • 2014
VIEW 1 EXCERPT

Luo Si

Qifan Wang, Lingyun Ruan
  • Adaptive knowledge transfer for multiple instance learning in image classification. AAAI Conference on Artificial Intelligence,
  • 2014
VIEW 1 EXCERPT

Paul Ruvolo

Haitham Bou Ammar, Eric Eaton
  • Online multi-task learning for policy gradient methods. International Conference on Machine Learning,
  • 2014

Yueting Zhuang

Zhou Yu, Fei Wu, Yi Yang, Qi Tian, Jiebo Luo
  • Discriminative coupled dictionary hashing for fast cross-media retrieval. International ACM SIGIR Conference on Research & Development in Information Retrieval,
  • 2014
VIEW 3 EXCERPTS