Skip to main content
2 votes
Accepted

Non-Neural Network algorithms for large state space in zero sum games

I was reading online that tic-tac-toe has a state space of $3^9 = 19,683$. From my basic understanding, this sounds too large to use tabular Q-learning, as the Q table would be huge. Is this correct? ...
Neil Slater's user avatar
  • 32.7k
2 votes
Accepted

Q learning (DQN) strategy for a multiplayer zero-sum game

This works, and is used as a standard approach for two player zero-sum games in reinforcement learning. As you stated, it is a combination of reinforcement learning with Minimax optimisation. A very ...
Neil Slater's user avatar
  • 32.7k
1 vote
Accepted

Optimal mixed strategy in two player zero sum games

I will answer the first question question based on information I have gathered so far. The probability of each action for the $\textbf{two player zero sum game}$ need not be the same for both players. ...
calveeen's user avatar
  • 1,281

Only top scored, non community-wiki answers of a minimum length are eligible