Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @togelius
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @togelius
-
Prikvačeni tweet
What if we see level generation as a game, where each action changes the level in some way? Well, we could use RL to learn to "play" level generation! We introduce Procedural Content Generation via Reinforcement Learning (PCGRL), a new paradigm for PCG. https://arxiv.org/abs/2001.09212 pic.twitter.com/J9c8O5EIM7
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This is the kind of artist I would be if I was an artist.https://twitter.com/StevenJCrowley/status/1223977380794064897 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Julian Togelius proslijedio/la je Tweet
Wow: Google's "Meena" chatbot was trained on a full TPUv3 pod (2048 TPU cores) for **30 full days** - That's more than $1,400,000 of compute time to train this chatbot model. (! 100+ petaflops of sustained compute !)pic.twitter.com/BiPdTTG5E9
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Julian Togelius proslijedio/la je Tweet
Dear fellow conference paper reviewers: Smith (2009) without including the full reference is not helpful feedback. Take a second copy and paste the reference from Google Scholar if you really want to help the author, rather than make you feel smug about yourself.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Julian Togelius proslijedio/la je Tweet
it's faculty job hunting season! i wrote up the advice i give my students and others as they start interviewing. tips are mostly relevant to HCI/CS interviews :: http://www.jeffreybigham.com/blog/2020/faculty-job-interviewing-tips.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Julian Togelius proslijedio/la je Tweet
To the left, you see a trained agent playing a level of a game. To the right, you see the same playthrough from an agent-centric perspective: cropped, translated, and rotated with the agent in the center. Which perspective is the best input for the agent? https://arxiv.org/abs/2001.09908 pic.twitter.com/7bCtBp8xUG
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
In any case, even if this is possible in principle, it seems that the way we represent the input makes a lot of difference for the generality of skills that can be learned in practice.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
It is possible that the standard paradigm of a neural network with a handful of layers learning to master, say, Atari games from a static third-person view is actually impossible. That is, it doesn't learn any general playing skills. It learns some kind of stimulus-response table
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Also, can it? It is hard to imagine that a neural network of just a few layers could actually implement the transformations necessary to even understand where things are relative to the agent, so that the policy can be location-independent?
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The promise/premise of deep learning is that we don't have to worry about these representations, because the network will figure out the input representation itself. But, really, will it? Will a network of a few layers really learn to rotate and translate to focus on the agent?
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
It is well known from "non-deep" agent learning research (say, evolutionary robotics work and game AI work from early to mid 2000s) that the sensor representation is extremely important to the agent's ability to learn. http://julian.togelius.com/VanHoorn2009Hierarchical.pdf …pic.twitter.com/Ugj9IDsdDR
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This paper builds on earlier work, where we showed that standard deep RL algorithms learn policies that generalize very badly. They are barely able to play any levels that they were not trained on at all.https://twitter.com/togelius/status/1012726654261702658 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Note that in all six conditions, the algorithm is able to learn policies that work on the specific level(s) it is trained on. What really differs is the generalization capacity.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Simply cropping the level to see only what's around the agent, or rotating it so that the agent is pointing up, or translating it so that the agent is always in the center of the image, have little effect on their own. But all three together drastically increases generalization!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We use a standard deep network architecture and reinforcement learning algorithm (A2C). When agents are trained using the top-down view which is the game's "native" view (to the left in the inital gif) the trained networks play unseen levels very badly.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
In our new paper, "Rotation, Translation, and Cropping for Zero-Shot Generalization" by
@yooceii@Amidos2006@FilipoGiovanni and I show that the agent-centric perspective is better in the sense that the agent learns policies that generalize better. https://arxiv.org/abs/2001.09908 pic.twitter.com/q7jLjBRjLL
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
To the left, you see a trained agent playing a level of a game. To the right, you see the same playthrough from an agent-centric perspective: cropped, translated, and rotated with the agent in the center. Which perspective is the best input for the agent? https://arxiv.org/abs/2001.09908 pic.twitter.com/7bCtBp8xUG
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
"It is a truth universally acknowledged, that a single agent in possession of a good reward, must be in want of an environment." (This sentence was just deleted from the ICML abstract that
@FilipoGiovanni and I are writing)Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Julian Togelius proslijedio/la je Tweet
Legitimately one of the best insights I've internalized after years of doing research is the old classic - "ideas are cheap, execution is everything" [not quite everything, we still need cool ideas, but y'know]https://twitter.com/JoeKanja7/status/1222766508218159105 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Julian Togelius proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Julian Togelius proslijedio/la je Tweet
imagine how much more comprehensible academic papers would be if literacy in visual communication was as universal as literacy in writing idk why we treat diagrams & illustrations as subordinate to the written parts of papers when they’re often more important for comprehension
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.