Setting ourselves up for exploitation: RL in the wild

Linking pages

The Importance of Hyperparameter Optimization for Model-based Reinforcement Learning – The Berkeley Artificial Intelligence Research Blog https://bair.berkeley.edu/blog/2021/04/19/mbrl/ 0 comments
How all machine learning becomes reinforcement learning https://robotic.substack.com/p/ml-becomes-rl 0 comments
Using RL's exploitation to debug - by Nathan Lambert https://robotic.substack.com/p/rl-to-debug-systems 0 comments

Linked pages

Machine Learning: The Great Stagnation - by Mark Saroufim https://marksaroufim.substack.com/p/machine-learning-the-great-stagnation 218 comments
He got Facebook hooked on AI. Now he can't fix its misinformation addiction | MIT Technology Review https://www.technologyreview.com/2021/03/11/1020600/facebook-responsible-ai-misinformation/ 112 comments
Specification gaming: the flip side of AI ingenuity https://deepmind.com/blog/article/Specification-gaming-the-flip-side-of-AI-ingenuity 31 comments
Specification gaming examples in AI - master list - Google Drive https://docs.google.com/spreadsheets/u/1/d/e/2PACX-1vRPiprOaC3HsCf5Tuum8bRfzYUiKLRqJmbOoC-32JorNdfyTiRRsR7Ea5eWtvsWzuxo8bjOxCG84dAg/pubhtml 28 comments
Control theory - Wikipedia https://en.wikipedia.org/wiki/Control_theory 10 comments
Bellman equation - Wikipedia https://en.wikipedia.org/wiki/Bellman_equation 6 comments
On YouTube Kids, Startling Videos Slip Past Filters - The New York Times https://www.nytimes.com/2017/11/04/business/media/youtube-kids-paw-patrol.html 4 comments
[1812.02353] Top-K Off-Policy Correction for a REINFORCE Recommender System https://arxiv.org/abs/1812.02353 3 comments
[2102.13651] On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning https://arxiv.org/abs/2102.13651 2 comments
Nuremberg trials - Wikipedia https://en.wikipedia.org/wiki/Nuremberg_trials#Intelligence_tests_and_psychiatric_assessments 1 comment
Instrumental convergence - Wikipedia https://en.wikipedia.org/wiki/Instrumental_convergence 0 comments
On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning https://www.natolambert.com/papers/2021-hyperparams-mbrl 0 comments