A tentative schedule of upcoming 2018 talks:
- Friday 23 March 11:00-12:00 in Snellius 167: Thomas Moerland: Thinking Fast & Slow with Deep Learning and Tree Search
- Friday 6 April 11:00-12:00 in Snellius 167: Aske Plaat: AlphaGo Slides
- Monday 16 April 14:00-15:00 in Snellius 167: Wojtek Kowalczyk: Deep Learning 4 Reinforcement Learning part 1: CNN – The Brain of AlphaGo
- Monday 30 April 14:00-15:00 in Snellius 167: Wojtek Kowalczyk: Deep Learning 4 Reinforcement Learning part 2: Training the Brain of AlphaGo
- Monday 14 May 14:00-15:00 in Snellius 167: Open discussion, for example on the AlphaGo Zero General implementation of Othello, Connect-Four and TicTacToe in Python on Github
- Monday 28 May 14:00-15:00 in Snellius 167: Erwin Bakker: Robotics Reinforcement Learning paper
- Monday 27 August 14:00-15:00 in Snellius 167 same talk by Erwin Bakker
- TBD in Snellius 167: Hui Wang: Monte Carlo Q-learning
- TBD in Snellius 167: Michael Emmerich: Global Optimization and Reinforcement Learning
- TBD in Snellius 167: Kaifeng Yang: Reinforcement Learning and Bayesian Optimization
- TBD in Snellius 167: Master Students: AlphaChess, or Alfons Laarman: SAT
