NeurIPS 2020spotlight53 citations
Avoiding Side Effects in Complex Environments
Alex Turner, Neale Ratzlaff, Prasad Tadepalli
Abstract
Reward function specification can be difficult. Rewarding the agent for making a widget may be easy, but penalizing the multitude of possible negative side effects is hard. In toy environments, Attainable Utility Preservation (AUP) avoided side effects by penalizing shifts in the ability to achieve randomly generated goals. We scale this approach to large, randomly generated environments based on Conway's Game of Life. By preserving optimal value for a single randomly generated reward function, AUP incurs modest overhead while leading the agent to complete the specified task and avoid many side effects. Videos and code are available at https://avoiding-side-effects.github.io/.
BibTeX
@inproceedings{NEURIPS2020_f50a6c02,
author = {Turner, Alex and Ratzlaff, Neale and Tadepalli, Prasad},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {21406--21415},
publisher = {Curran Associates, Inc.},
title = {Avoiding Side Effects in Complex Environments},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/f50a6c02a3fc5a3a5d4d9391f05f3efc-Paper.pdf},
volume = {33},
year = {2020}
}