Automatically Mapped Transfer Between Reinforcement Learning Tasks via Three-Way Restricted Boltzmann Machines

Abstract

Existing reinforcement learning approaches are often hampered by learning tabula rasa . Transfer for reinforcement learning tackles this problem by enabling the reuse of previously learned results, but may require an inter-task mapping to encode how the previously learned task and the new task are related. This paper presents an autonomous framework for learning inter-task mappings based on an adaptation of restricted Boltzmann machines. Both a full model and a computationally efficient factored model are introduced and shown to be effective in multiple transfer learning scenarios.

Cite

Text

Bou-Ammar et al. "Automatically Mapped Transfer Between Reinforcement Learning Tasks via Three-Way Restricted Boltzmann Machines." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2013. doi:10.1007/978-3-642-40991-2_29

Markdown

[Bou-Ammar et al. "Automatically Mapped Transfer Between Reinforcement Learning Tasks via Three-Way Restricted Boltzmann Machines." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2013.](https://mlanthology.org/ecmlpkdd/2013/bouammar2013ecmlpkdd-automatically/) doi:10.1007/978-3-642-40991-2_29

BibTeX

@inproceedings{bouammar2013ecmlpkdd-automatically,
  title     = {{Automatically Mapped Transfer Between Reinforcement Learning Tasks via Three-Way Restricted Boltzmann Machines}},
  author    = {Bou-Ammar, Haitham and Mocanu, Decebal Constantin and Taylor, Matthew E. and Driessens, Kurt and Tuyls, Karl and Weiss, Gerhard},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2013},
  pages     = {449-464},
  doi       = {10.1007/978-3-642-40991-2_29},
  url       = {https://mlanthology.org/ecmlpkdd/2013/bouammar2013ecmlpkdd-automatically/}
}