Tweetovi

Blokirali ste korisnika/cu @FilipoGiovanni

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @FilipoGiovanni

  1. proslijedio/la je Tweet
    1. velj

    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?

    Prikaži ovu nit
    Poništi
  2. 28. sij

    Our new paper on training computer agents to design video game levels using reinforcement learning

    Poništi
  3. proslijedio/la je Tweet
    28. sij

    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.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    7. sij

    Introducing Deep Innovation Protection - we scale neuroevolution to more complex tasks such as "VizDoom: Take Cover" by temporally reducing the selection pressure on specific components in an evolving world model. w/

    Prikaži ovu nit
    Poništi
  5. 15. kol 2019.

    Cause and Effect is hard. Here we train an agent to invest with bankers and then wait for it’s riches. Our agent likes to stand in its lucky corner, where it happens to be, when the reward comes in. I think we’ve almost cracked human intelligence.

    Poništi
  6. proslijedio/la je Tweet

    Biometric scanning offers an extra level of security for everything from unlocking your cellphone to crossing borders. But as hackers grow more sophisticated, the war between privacy and exposure may be unwinnable.

    Poništi
  7. proslijedio/la je Tweet
    19. velj 2019.

    Happy our "Deep Learning for Video Game Playing" review article is now published in IEEE Transactions on Games: PDF: Lots of new methods added since the last update!

    Poništi
  8. proslijedio/la je Tweet
    6. pro 2018.

    We won! Great job everyone! So proud and excited to see what can become! Now time to get to work!

    Poništi
  9. proslijedio/la je Tweet
    7. ruj 2018.

    My new book, "Playing Smart: On Games, Intelligence, and Artificial Intelligence": This is a popular science book aimed at non-technical audiences. It's an overview of research on AI and games, and an argument that AI is crucial for games and vice versa.

    Prikaži ovu nit
    Poništi
  10. 10. kol 2018.

    One reason why DeepRL struggles generalizing to play visually similar, but functionally different levels for video games

    Poništi
  11. proslijedio/la je Tweet
    29. lip 2018.

    Deep reinforcement learning overfits. Often, a trained network can only play the particular level(s) you trained it on! In our new paper, we show how to train more general networks with procedural level generation, generating progressively harder levels.

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    8. lip 2018.

    You know what's better than video games for testing your RL algorithms? Why, a framework where you can easily make new games and levels! You can now use General Video Game AI with gym. In a first paper, we test deep RL algos on GVGAI games.

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    28. kol 2017.

    Draft version of survey: Deep Learning for Video Game Playing With

    Poništi
  14. proslijedio/la je Tweet
    24. svi 2017.

    Generating Fingerprints for Presentation Attacks, by . A GAN for Fingerprints.

    Poništi

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.

    Možda bi vam se svidjelo i ovo:

    ·