Learning Structured Decision Problems with Unawareness

Craig Innes, Alex Lascarides
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:2941-2950, 2019.

Abstract

Structured models of decision making often assume an agent is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we learn Bayesian Decision Networks from both domain exploration and expert assertions in a way which guarantees convergence to optimal behaviour, even when the agent starts unaware of actions or belief variables that are critical to success. Our experiments show that our agent learns optimal behaviour on both small and large decision problems, and that allowing an agent to conserve information upon making new discoveries results in faster convergence.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-innes19a, title = {Learning Structured Decision Problems with Unawareness}, author = {Innes, Craig and Lascarides, Alex}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {2941--2950}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/innes19a/innes19a.pdf}, url = {https://proceedings.mlr.press/v97/innes19a.html}, abstract = {Structured models of decision making often assume an agent is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we learn Bayesian Decision Networks from both domain exploration and expert assertions in a way which guarantees convergence to optimal behaviour, even when the agent starts unaware of actions or belief variables that are critical to success. Our experiments show that our agent learns optimal behaviour on both small and large decision problems, and that allowing an agent to conserve information upon making new discoveries results in faster convergence.} }
Endnote
%0 Conference Paper %T Learning Structured Decision Problems with Unawareness %A Craig Innes %A Alex Lascarides %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-innes19a %I PMLR %P 2941--2950 %U https://proceedings.mlr.press/v97/innes19a.html %V 97 %X Structured models of decision making often assume an agent is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we learn Bayesian Decision Networks from both domain exploration and expert assertions in a way which guarantees convergence to optimal behaviour, even when the agent starts unaware of actions or belief variables that are critical to success. Our experiments show that our agent learns optimal behaviour on both small and large decision problems, and that allowing an agent to conserve information upon making new discoveries results in faster convergence.
APA
Innes, C. & Lascarides, A.. (2019). Learning Structured Decision Problems with Unawareness. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:2941-2950 Available from https://proceedings.mlr.press/v97/innes19a.html.

Related Material