Black Swans

d

8 points

joined
d hasn't added a bio yet
History

History

This Study shows that overfitting in RL can occur

https://arxiv.org/abs/1804.06893

Title: A general reinforcement learning algorithm that masters chess, shogi and Go through self-play

Link: https://deepmind.com/research/publications/

Hi I am Dominic and I study Informatics at the Technical University of Berlin. I am deeply ( :) ) interested in various Topics regarding Machine Learning and Deep Learning and hope to work later in these Departments. Fascinating for me are AlphaZero and the new AlphaStar which proves how powerful AI already become. Furthermore I constantly think about games with imperfect Information like Poker. Hope to educate myself further through this group and peace out :)

I'm in :)