ML Anthology

Curiosity-Driven Exploration with Planning Trajectories

Tyler Streeter
AAAI 2006 pp. 1897-1898
/aaai/2006/streeter2006aaai-curiosity/

Abstract

Reinforcement learning (RL) agents can reduce learning time dramatically by planning with learned predictive models. Such planning agents learn to improve their actions using planning trajectories, sequences of imagined

PDF AAAI Semantic Scholar

Cite

Text

Streeter. "Curiosity-Driven Exploration with Planning Trajectories." AAAI Conference on Artificial Intelligence, 2006.

Markdown

[Streeter. "Curiosity-Driven Exploration with Planning Trajectories." AAAI Conference on Artificial Intelligence, 2006.](https://mlanthology.org/aaai/2006/streeter2006aaai-curiosity/)

BibTeX

@inproceedings{streeter2006aaai-curiosity,
  title     = {{Curiosity-Driven Exploration with Planning Trajectories}},
  author    = {Streeter, Tyler},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2006},
  pages     = {1897-1898},
  url       = {https://mlanthology.org/aaai/2006/streeter2006aaai-curiosity/}
}