COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Engineering Safe AI > Approaches to avoiding negative side effects
Approaches to avoiding negative side effectsAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Adrià Garriga Alonso. In this session we will learn about several approaches to avoiding negative side-effects, from the papers:
The first paper’s approach is reasonably efficient to compute. However, it only applies to discrete-state factored MDPs, the human feedback it requires probably doesn’t scale great, and it doesn’t account for all kinds of positive or negative side effects. The approaches from the second paper are less immediately applicable and difficult to compute. Both provide some insights, and we will base our discussion of how to improve side-effect measures on them. Relevant papers: “Minimax-Regret Querying on Side Effects for Safe Optimality in Factored Markov Decision Processes”, Shun Zhang, Edmund H. Durfee, and Satinder Singh, 2018, https://web.eecs.umich.edu/~baveja/Papers/ijcai-2018.pdf “Low Impact Artificial Intelligences”, Armstrong and Levinstein 2017 https://arxiv.org/abs/1705.10720 “AI Safety Gridworlds”, Leike et al. 2017, https://arxiv.org/abs/1711.09883 “Concrete Problems in AI Safety”, Amodei et al. 2016 https://arxiv.org/abs/1606.06565 This talk is part of the Engineering Safe AI series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsHigh dimensional statistics CISA Gypsy Roma Traveller (GRT) History MonthOther talksOpening Flies’ Ears and Head-Heart My Life in Science Seminar “Publishing in Science: an Inside Look" In-Network Computing: Your network just got a lot smarter Grenfell Tower - One Year On Constructing the organism in the age of abstraction |