RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments

Shivam Goel and Yash Shukla and Vasanth Sarathy and Matthias Scheutz and Jivko Sinapov

We propose an integrated planning and learning approach that utilizes learning from failures and transferring knowledge over time to overcome novelty scenarios. The approach is more sample efficient in adapting to sudden and unknown changes (i.e., novelties) than the existing hybrid approaches. We showcase our results on a Minecraft-inspired gridworld environment called NovelGridworlds by injecting three novelties in the agent’s environment at test time. We show that our approach can speed up continual learning through information gained in each novel experience and, thus, more sample-efficient.

@inproceedings{goeletal22icdl,
  title={RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments},
  author={Shivam Goel and Yash Shukla and Vasanth Sarathy and Matthias Scheutz and Jivko Sinapov},
  year={2022},
  booktitle={Proceedings of International Conference on Development
                  and Learning},
  url={https://hrilab.tufts.edu/publications/goeletal22icdl.pdf}
}