2
votes
Accepted
How should I define the reward function in the case of Connect Four?
The classic working reward scheme for two player zero sum games (i.e. if I win, you lose and vice versa) is simply:
+1 for a win
0 for a draw
-1 for a loss
These rewards should be associated with ...
1
vote
Accepted
Deep Reinforcement Learning - How to Avoid a Naive Solution?
There are many potential reasons why your AI might be learning that it's best to put $4$ pieces in the same column. One possibility is that AI is simply finding this strategy to be the most effective ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
connect-four × 5reinforcement-learning × 2
deep-learning × 1
q-learning × 1
deep-rl × 1
dqn × 1
game-ai × 1
rewards × 1
minimax × 1
reward-design × 1
sarsa × 1
hill-climbing × 1
evaluation-functions × 1
heuristic-functions × 1
quiescence-search × 1
negamax × 1