Deep Anti-Determinism - by Lydia Nottingham - pronotre

This machinery matters to me…

This machinery matters to me… Say there’s some event you care about, E. You want E to happen. Initially, your default policy is π_0, and you estimate P(E | π_0) < 1. But since you want E to happen, you come up with a new plan, π_1, to make E more likely. Now you calculate P(E | π_1) and check: are you satisfied? If not, you devise a new plan, π_2, and calculate P(E | π_2). If each plan is better than the last, you’ll obtain a monotone increasing sequence of probability forecasts. By Monotone Convergence Theorem, this sequence will converge to sup(P(E | π_k)). There’s an intuition going…

saved by

• Omkar Gadewar
• Alejo Acelas

related reading

• the trouble with making predictions as an agentsubstack.com
• Deep Deceptiveness — LessWronglesswrong.com
• Towards a scale-free theory of intelligent agencymindthefuture.info
• pdfopenreview.net
• Deep Reinforcement Learning: Pong from Pixelskarpathy.github.io
• Embedded Agency (full-text version) — LessWronglesswrong.com
• Open-minded updatelessness — LessWronglesswrong.com
• Updatelessness doesn't solve most problems — LessWronglesswrong.com
• Probabilities are not the right concept — LessWronglesswrong.com
• Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
• Thoughts on Updatelessness &#8211; The Universe from an Intentional Stancecasparoesterheld.com
• Deep Reinforcement Learning: Pong from Pixelskarpathy.github.io