Questions tagged [self-play]
For questions about the technique of "self play" in reinforcement learning in relation to combinatorial games and games in general.
4
questions
3
votes
2
answers
914
views
How can both agents know the terminal reward in self-play reinforcement learning?
There seems to be a major difference in how the terminal reward is received/handled in self-play RL vs "normal" RL, which confuses me.
I implemented TicTacToe the normal way, where a single ...
- 91
6
votes
2
answers
3k
views
Why does self-playing tic-tac-toe not become perfect?
I trained a DQN that learns tic-tac-toe by playing against itself with a reward of -1/0/+1 for a loss/draw/win. Every 500 episodes, I test the progress by letting it play some episodes (also 500) ...
- 91
3
votes
1
answer
242
views
How does MuZero learn to play well for both sides of a two-player game?
I'm coding my own version of MuZero. However, I don't understand how it supposed to learn to play well for both players in a two-player game.
Take Go for example. If I use a single MCTS to generate an ...
- 170
3
votes
1
answer
210
views
Given these two reward functions, what can we say about the optimal Q-values, in self-play tic-tac-toe?
This corresponds to Exercise 1.1 of Sutton & Barto's book (2nd edition), and a discussion followed from this answer.
Consider the following two reward functions
Win = +1, Draw = 0, Loss = -1
Win =...
- 211