Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @vkrakovna
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @vkrakovna
-
Victoria Krakovna proslijedio/la je Tweet
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 -
Victoria Krakovna proslijedio/la je Tweet
RL shifts the question of what intelligent behavior is to finding a reward function. I think we should focus more on what environment and reward function rather than on what RL algorithm to use. Is there theory for how properties of env and reward affect the resulting behavior?https://twitter.com/KaiLashArul/status/1213526645438648320 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Victoria Krakovna proslijedio/la je Tweet
Join us for our final podcast of 2019 with
@harari_yuval and@tegmark on consciousness, ethics, effective altruism, human extinction, emerging technologies, and the role of myths and stories in fostering societal collaboration and meaning.https://futureoflife.org/2019/12/31/on-consciousness-morality-effective-altruism-myth-with-yuval-noah-harari-max-tegmark/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
My current thoughts on the specification gaming examples list (1.5 years after its release)https://vkrakovna.wordpress.com/2019/12/20/retrospective-on-the-specification-gaming-examples-list/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Victoria Krakovna proslijedio/la je Tweet
In this episode of AIAP, Jan Leike discusses his movement from theoretical to empirical AI safety research — why empirical safety research is important, how this has lead him to his work on recursive reward modeling, and the work being done at DeepMind.https://futureoflife.org/2019/12/16/ai-alignment-podcast-on-deepmind-ai-safety-and-recursive-reward-modeling-with-jan-leike/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Victoria Krakovna proslijedio/la je Tweet
We present ReQueST: a method for training RL agents from human feedback in the presence of unknown unsafe states. By
@sidgreddy,@ancadianadragan,@svlevine,@ShaneLegg,@janleike Paper: https://arxiv.org/abs/1912.05652 Code: https://github.com/rddy/ReQueST pic.twitter.com/qM8GSaMcr2
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Victoria Krakovna 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 -
Victoria Krakovna proslijedio/la je Tweet
Stuart Russell discusses his newest book on the AI Alignment Podcast, Human Compatible: Artificial Intelligence and the Problem of Control.https://futureoflife.org/2019/10/08/ai-alignment-podcast-human-compatible-artificial-intelligence-and-the-problem-of-control-with-stuart-russell/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Open-source code for the paper "Penalizing side effects using stepwise relative reachability", comparing different design choices for side effects penalties:https://github.com/deepmind/deepmind-research/tree/master/side_effects_penalties …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The fourth episode of the new
@DeepMindAI podcast discusses specification problems in AI safety, Goodhart's Law, and reward learning.https://deepmind.com/blog/article/podcast-episode-4-ai-robot …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
New blog post on classifying AI safety problems as different types of Goodhart's lawhttps://vkrakovna.wordpress.com/2019/08/19/classifying-specification-problems-as-variants-of-goodharts-law/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If you're interested in
@DeepMindAI's safety work, it is now all in one place on the new websitehttps://deepmind.com/research?filters=%7B%22tags%22:%5B%22Safety%22%5D%7D …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Exciting work on the reward tampering problem in AI safety, where the agent changes its reward function by exploiting how reward is implemented in the environment. The paper proposes design principles for building agents without an incentive to tamper with the reward function.https://twitter.com/DeepMind/status/1161665660293980160 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Victoria Krakovna proslijedio/la je Tweet
Research Engineer required in our
@deepmindAI Safety Team -#deepmind#safety#engineeringroles https://deepmind.com/careers/1433588/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
New paper on modeling AI safety approaches with causal influence diagrams https://arxiv.org/abs/1906.08663
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Victoria Krakovna proslijedio/la je Tweet
FLI's
@vkrakovna co-organized the Safe Machine Learning workshop at@iclr2019. Read her recap of the event for an overview of the talks, panels, and papers. https://buff.ly/2ZAieeu pic.twitter.com/AziyMWHyCb
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
My belated summary of the Safe ML workshop at ICLRhttp://vkrakovna.wordpress.com/2019/06/18/iclr-safe-ml-workshop-report …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Victoria Krakovna proslijedio/la je Tweet
Very excited to deliver the
#icml2019 tutorial on#safeml tomorrow together with@csilviavr! Be prepared for fairness, human-in-the-loop RL, and a general overview of the field. And lots of memes!pic.twitter.com/o0zrDPLYxo
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Victoria Krakovna proslijedio/la je Tweet
DeepMind’s
@pushmeet spoke to@80000Hours about the importance of building robust and safe AI systems. Listen to the full podcast to find out why a career in machine learning makes a difference:https://80000hours.org/podcast/episodes/pushmeet-kohli-deepmind-safety-research/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Separate recordings of SafeML talks are now available on the workshop websitehttps://sites.google.com/corp/view/safeml-iclr2019/schedule …
Prikaži ovu nitHvala. 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.