Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
Blokirali ste korisnika/cu @tom4everitt
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @tom4everitt
-
Tom Everitt proslijedio/la je Tweet
Nice example of how SCM can serve as a laboratory to test various interpretations of familiar and colloquially used terms, in this case "incentives".
#Bookofwhyhttps://twitter.com/tom4everitt/status/1220657129264177152 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thanks to structural causal models, we now a more precise understanding of incentives in causal influence diagrams blog post: https://medium.com/@RyanCarey/d6d8bb77d2e4 … arXiv: https://arxiv.org/abs/2001.07118
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tom Everitt proslijedio/la je Tweet
We have 2 papers published in
@nature today!
One describes AlphaFold, which uses deep neural networks to predict protein structures with high accuracy. AlphaFold made the most accurate predictions at the 2018 scientific community assessment CASP13. 1/4https://deepmind.com/blog/article/AlphaFold-Using-AI-for-scientific-discovery …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
nice game theoretic analysis of debate as an AI safety methodhttps://twitter.com/ryancareyai/status/1210320486888038400 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Model-based RL can be really helpful for safety. Great work!https://twitter.com/janleike/status/1205488664106524672 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tom Everitt proslijedio/la je Tweet
How do you train an RL agent in the presence of unknown, unsafe states without visiting them even once? New algorithm by our intern
@sidgreddy synthesizes trajectories with a generative model and ask a human to label them for safety.https://deepmind.com/blog/article/learning-human-objectives-by-evaluating-hypothetical-behaviours …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tom Everitt proslijedio/la je Tweet
With time, we hope these design principles can help inform best practices for how to build capable RL agents without reward tampering incentives. This builds upon our previous work on understanding agent incentives with causal influence diagrams:https://medium.com/@deepmindsafetyresearch/understanding-agent-incentives-with-causal-influence-diagrams-7262c2512486 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tom Everitt proslijedio/la je Tweet
In our latest AI safety blog post, we explore principled solutions to the reward tampering problem, in which a reinforcement learning agent actively changes its reward function to maximise reward. Blog post: https://medium.com/@deepmindsafetyresearch/designing-agent-incentives-to-avoid-reward-tampering-4380c1bb6cd … Paper: https://arxiv.org/abs/1908.04734 pic.twitter.com/HRnoYBHBYA
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
How can we make sure that agents work to achieve their intended task instead of tampering with their reward mechanism? Reward tampering problems correspond to undesired causal paths in causal influence diagrams, and solutions to ways of removing the paths.https://medium.com/@deepmindsafetyresearch/designing-agent-incentives-to-avoid-reward-tampering-4380c1bb6cd …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tom Everitt proslijedio/la je Tweet
another step towards developing a set of best practices for designing safe RL agents - in this case, by avoiding incentives for agents to tamper with their own reward function. great work,
@tom4everitt and team
https://twitter.com/DeepMind/status/1161665660293980160 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tom Everitt proslijedio/la je Tweet
Many AI safety problems are about agent incentives. In our latest blog post, we suggest a systematic study of agent incentives based on influence diagrams and graphical criteria for different types of incentives. Blog post: https://medium.com/@deepmindsafetyresearch/understanding-agent-incentives-with-causal-influence-diagrams-7262c2512486 … Paper: https://arxiv.org/abs/1902.09980
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tom Everitt proslijedio/la je Tweet
The agent alignment problem may be one of the biggest obstacles for using ML to improve people’s lives. Today I’m very excited to share a research direction for how we’ll aim to solve alignment at
@DeepMindAI. Blog post: https://medium.com/@deepmindsafetyresearch/scalable-agent-alignment-via-reward-modeling-bf4ab06dfd84 … Paper: https://arxiv.org/pdf/1811.07871.pdf …pic.twitter.com/33HQTlkcQR
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.