Mariya Tsvarkaleva, Louise A. Dennis. No Free Lunch: Overcoming Reward Gaming in AI Safety Gridworlds. In Ibrahim Habli, Mark Sujan, Simos Gerasimou, Erwin Schoitsch, Friedemann Bitsch, editors, Computer Safety, Reliability, and Security. SAFECOMP 2021 Workshops - DECSoS, MAPSOD, DepDevOps, USDAI, and WAISE, York, UK, September 7, 2021, Proceedings. Volume 12853 of Lecture Notes in Computer Science, pages 226-238, Springer, 2021. [doi]
@inproceedings{TsvarkalevaD21, title = {No Free Lunch: Overcoming Reward Gaming in AI Safety Gridworlds}, author = {Mariya Tsvarkaleva and Louise A. Dennis}, year = {2021}, doi = {10.1007/978-3-030-83906-2_18}, url = {https://doi.org/10.1007/978-3-030-83906-2_18}, researchr = {https://researchr.org/publication/TsvarkalevaD21}, cites = {0}, citedby = {0}, pages = {226-238}, booktitle = {Computer Safety, Reliability, and Security. SAFECOMP 2021 Workshops - DECSoS, MAPSOD, DepDevOps, USDAI, and WAISE, York, UK, September 7, 2021, Proceedings}, editor = {Ibrahim Habli and Mark Sujan and Simos Gerasimou and Erwin Schoitsch and Friedemann Bitsch}, volume = {12853}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, isbn = {978-3-030-83906-2}, }