Profile cover photo
Profile photo
Ioannis Kourouklides
319 followers -
AI Researcher - Data Scientist
AI Researcher - Data Scientist

319 followers
About
Posts

Post has shared content

Post has attachment

#Uber #AI Labs Open Sources #Pyro, a Deep Probabilistic Programming Language

Post has shared content

Post has shared content

Post has shared content
Ensemble meta-learning works also for RL (Reinforcement Learning). Read how DeepMind got it done with Rainbow which combines six extensions to the DQN (Deep Q-Networks) algorithm: A3C, DDQN, Prioritized DDQN,Dueling DDQN, Distributional DQN, and Noisy DQN. The paper, abstract: https://goo.gl/wNwgjG, full (PDF): https://goo.gl/M5RZah

Post has shared content

Post has shared content

Post has shared content

Post has attachment
Wait while more posts are being loaded