Reinforcement Learning
What an agent receives after performing an action
Reward
One limitation of AlphaGo
Can't play anything besides Go/can't transfer skills from Go to a different game
The ability of a program to transfer what it has learned about one task to help it perform a different, related task
Transfer learning
What are Deep Q-learning systems still failing at/unable to achieve
abstraction/domain generalization/transfer learning
The game platform used by the DeepMind programmers in their work on reinforcement learning.
Atari