Difference between revisions of "Gaming"
(→OpenAI: Dota 2 ...2018) |
|||
| Line 23: | Line 23: | ||
<youtube>XbDmxEOj9OY</youtube> | <youtube>XbDmxEOj9OY</youtube> | ||
| − | == OpenAI: Dota 2 ...2018 == | + | == [http://openai.com/ OpenAI]: Dota 2 ...2018 == |
<youtube>eHipy_j29Xw</youtube> | <youtube>eHipy_j29Xw</youtube> | ||
<youtube>wiOopO9jTZw</youtube> | <youtube>wiOopO9jTZw</youtube> | ||
Revision as of 09:26, 2 January 2019
- Case Studies
- Google DeepMind AlphaGo Zero
- Reinforcement Learning (RL)
- Deep Q Learning (DQN)
- Competitions
- An introduction to Deep Q-Learning: let’s play Doom
- AI and Games Series; an Informed Overview | Dr Tommy Thompson
- Game Changer: AlphaZero's Groundbreaking Chess Strategies and the Promise of AI | M. Sadler and N. Regan
Contents
OpenAI: Dota 2 ...2018
Google DeepMind AlphaGo: Go ...2016
Google DeepMind: Atari video games ...2015
IBM Watson: Jeopardy ...2011
IBM Deep Blue: Chess ...1997
Donald Waterman: Draw Poker ...1968
Arthur Samuel: Checkers ...1950s
