Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @pyoudeyer
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @pyoudeyer
-
Prikvačeni tweet
Our new
#Corl18 paper: How curiosity-driven autonomous goal setting enables to discover independantly controllable features of environments pdf: https://arxiv.org/abs/1807.01521 Blog: https://openlab-flowers.inria.fr/t/discovery-of-independently-controllable-features-through-autonomous-goal-setting/494 … Colab: https://colab.research.google.com/drive/176q8pnshfiQx4WFHPc4PiwmsijM4pKiz …#machinelearning#AI#NeuralNetworksPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
We investigated this in our
@iclr_conf 2020 paper with the IMGEP-OGL algorithm, to discover novel "animal" forms in Lenia, a continuous game of life from@BertChakovsky Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems https://arxiv.org/abs/1908.06663Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
One scientific challenge in this area is how to learn useful representations of goal spaces while exploring and making discoveries in such high-dimensional systems (e.g. in these wet experiments, the goal space was engineered by the hand, but how to learn it from pixels?)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This extends the Explauto library: https://github.com/flowersteam/explauto … dedicated to population-based IMGEP algorithms, developed by
@Clement_MF_@forestier_seb and@RouanetPierre@FlowersINRIAPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The code used in
@jgrizou et al.'s paper is available here:https://github.com/croningp/dropfactory_exploration …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The particular IMGEP algorithm used in these wet experiments samples goals randomly, leveraging a learned forward model + stochastic optimization to infer the corresponding params. to try. It is described in https://www.frontiersin.org/articles/10.3389/frobt.2016.00008/full … (wth L-BFGS instead of CMA-ES)
@FBenureauPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Great work showing how intrinsically motivated goal exploration can be used to automate discovery of novel patterns in wet chemical systems !!! Congratulations
@jgrizou and team! Intrinsically motivated#machinelearning algorithms open new perspectives in physics/chemistryhttps://twitter.com/jgrizou/status/1224304943147909120 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Pierre-Yves Oudeyer proslijedio/la je Tweet
1/ Did you know that Vannevar Bush (you know, the guy who helped enable everything from radar to the manhattan project, the NSF to memexes) wrote an autobiography? Turns out that yes he did, it's been out of print since the 70's, and it's *excellent* BOOK REPORT THREAD
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Pierre-Yves Oudeyer proslijedio/la je Tweet
There is also this great blog post by the same author (Cedric Colas) that's a bit more accessible:https://openlab-flowers.inria.fr/t/how-many-random-seeds-should-i-use-statistical-power-analysis-in-deep-reinforcement-learning-experiments/457 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Pierre-Yves Oudeyer proslijedio/la je Tweet
This is such a useful resource for understanding AI Ethics and Safety and it shows so clearly that AI is a multi-disciplinary field. https://www.turing.ac.uk/sites/default/files/2019-06/understanding_artificial_intelligence_ethics_and_safety.pdf …pic.twitter.com/DYKf38E2Uf
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Pierre-Yves Oudeyer proslijedio/la je Tweet
RL! What is it good for? Actually... Real world robotics!https://twitter.com/CovariantAI/status/1222560287124930560 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thanks to all contributors and to
@FBenureau for helping me editing the newsletter!Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I invite all readers interested to participate to this dialog to send me their response by June 30th, 2020. The length of each response must be between 600 and 800 words including references.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
However, a key challenge is how to measure progress in this area, as traditional RL benchmarks were not constructed to address open-ended learning.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Another related line of work is open-ended evolution in multi-agent systems with co-evolution.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Several steps in this direction have been made in the last decade, such as algorithms enabling agents to imagine their own goals and self-organize their learning curriculum (initially in the CDS community, and recently extended in the machine learning community).
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
While impressive progress was made recently in reinforcement learning, as shown in benchmarks with a set of pre-defined external objectives, a major challenge is now to build autonomous agents that can progressively discover and learn open repertoires of skills in open worlds.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Then, a new dialog initiation is proposed by
@Clement_MF_ on a fundamental question for the future of AI: How to evaluate open-ended learning agents?Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
They also offer a perspective on how artificial intelligence can play a key role in impactful educational apps, enabling to implement personalized and motivating learning strategies
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.