vs
- Human v Computer
- Human v Human
- Minimax
- Q-Learning
The algorithm used is Q-learning.
The agent has trained for 500000 games to populate the Q-Table.
The Q-table dictates the agent function of the agent.
- 1
- 2
- 3
- 4
- Unlimited
- Human
- Computer
Press "New Game" after changing options
Press to get a hint