Improving Reinforcement Learning with Human Input

Abstract

Reinforcement learning (RL) has had many successes when learning autonomously. This paper and accompanying talk consider how to make use of a non-technical human participant, when available. In particular, we consider the case where a human could 1) provide demonstrations of good behavior, 2) provide online evaluative feedback, or 3) define a curriculum of tasks for the agent to learn on. In all cases, our work has shown such information can be effectively leveraged. After giving a high-level overview of this work, we will highlight a set of open questions and suggest where future work could be usefully focused.

Cite

Text

Taylor. "Improving Reinforcement Learning with Human Input." International Joint Conference on Artificial Intelligence, 2018. doi:10.24963/IJCAI.2018/817

Markdown

[Taylor. "Improving Reinforcement Learning with Human Input." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/taylor2018ijcai-improving/) doi:10.24963/IJCAI.2018/817

BibTeX

@inproceedings{taylor2018ijcai-improving,
  title     = {{Improving Reinforcement Learning with Human Input}},
  author    = {Taylor, Matthew E.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {5724-5728},
  doi       = {10.24963/IJCAI.2018/817},
  url       = {https://mlanthology.org/ijcai/2018/taylor2018ijcai-improving/}
}