• Corpus ID: 239616157

Self-Initiated Open World Learning for Autonomous AI Agents

@article{Liu2021SelfInitiatedOW,
  title={Self-Initiated Open World Learning for Autonomous AI Agents},
  author={Bing Liu and Eric Robertson and Scott Grigsby and Sahisnu Mazumder},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.11385}
}
As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can learn by themselves in a self-motivated and selfsupervised manner rather than being retrained periodically on the initiation of human engineers using expanded training data. As the real-world is an open environment with unknowns or novelties, detecting novelties or unknowns, gathering ground-truth training data, and incrementally learning the unknowns make the… 

References

SHOWING 1-10 OF 18 REFERENCES
Towards a Unifying Framework for Formal Theories of Novelty
TLDR
This work presents the first unified framework for formal theories of novelty and uses the framework to formally define a family of novelty types, which can be applied across a wide range of domains, from symbolic AI to reinforcement learning, and beyond to open world image recognition.
Challenges of real-world reinforcement learning: definitions, benchmarks and analysis
TLDR
This work identifies and formalizes a series of independent challenges that embody the difficulties that must be addressed for RL to be commonly deployed in real-world systems and proposes an as an open-source benchmark.
Learning on the Job: Online Lifelong and Continual Learning
TLDR
On-the-job learning aims to leverage the learned knowledge to discover new tasks, interact with humans and the environment, make inferences, and incrementally learn the new tasks on the fly during applications in a self-supervised and interactive manner.
Lifelong Machine Learning
  • Zhiyuan Chen, B. Liu
  • Computer Science
    Synthesis Lectures on Artificial Intelligence and Machine Learning
  • 2016
TLDR
As statistical machine learning matures, it is time to make a major effort to break the isolated learning tradition and to study lifelong learning to bring machine learning to new heights.
Learning Cumulatively to Become More Knowledgeable
TLDR
Experimental results on two datasets with learning from 2 classes to up to 100 classes show that the proposed approach is highly promising in terms of both classification accuracy and computational efficiency.
Continual Lifelong Learning with Neural Networks: A Review
Lifelong and Continual Learning Dialogue Systems: Learning during Conversation
TLDR
This paper proposes to dramatically improve the situation by endowing the chatbots the ability to continually learn new world knowledge, new language expressions to ground them to actions, and new conversational skills, during conversation by themselves so that as they chat more and more with users, they become more andMore knowledgeable.
Towards Open World Recognition
  • Abhijit Bendale, T. Boult
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
It is proved that thresholding sums of monotonically decreasing functions of distances in linearly transformed feature space can balance “open space risk” and empirical risk and it is presented the Nearest Non-Outlier (NNO) algorithm that evolves model efficiently, adding object categories incrementally while detecting outliers and managing open space risk.
An Application-Independent Approach to Building Task-Oriented Chatbots with Interactive Continual Learning
Many real-life task-oriented chatbots are natural language (command) interfaces (NLIs) to their underlying applications. Such a NLI is often built using a semantic parser (SP) to parse the user
Unseen Class Discovery in Open-world Classification
  • Lei Shu, Hu Xu, Bing Liu
  • Computer Science, Mathematics
    ArXiv
  • 2018
TLDR
A joint open classification model with a sub-model for classifying whether a pair of examples belongs to the same or different classes is proposed that can serve as a distance function for clustering to discover the hidden classes of the rejected examples.
...
1
2
...