Questions tagged [self-play]
For questions about the technique of "self play" in reinforcement learning in relation to combinatorial games and games in general.
14
questions
2
votes
1answer
198 views
How to fight with unstability in self play?
I'm working on a neural network that plays some board games like reversi or tic-tac-toe (zero-sum games, two players). I'm trying to have one network topology for all the games - I specifically don't ...
3
votes
1answer
71 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 ...
1
vote
0answers
42 views
What does self-play in reinforcement learning lead to?
Suppose, instead of playing against a random opponent, the reinforcement learning algorithm described above played against itself, with both sides learning. What do you think would happen in this case?...
1
vote
2answers
66 views
Generalising performance of Q-learning agent through self-play in a two-player game (MCTS?)
I'm using Q-learning (off-policy TD-control as specified in Sutton's book on pg 131) to train an agent to play connect four. My goal is to create a strong player (superhuman performance?) purely by ...
3
votes
0answers
139 views
How to correctly implement self-play with DQN?
I have an environment where an agent faces an equal opponent, and while I've achieved OK performance implementing DQN and treating the opponent as a part of the environment, I think performance would ...
1
vote
0answers
48 views
Is it possible to use just one policy in a self-play setting? [closed]
I would like to ask is it possible to train an agent under self-playing setting but with just one policy to be trained? What are the foreseeable problems with such an implementation? My concern is as ...
3
votes
0answers
50 views
How exactly does self-play work, and how does it relate to MCTS?
I am working towards using RL to create an AI for a two-player, hidden-information, a turn-based board game. I have just finished David Silver's RL course and Denny Britz's coding exercises, and so am ...
4
votes
1answer
91 views
In AlphaZero, which policy is saved in the dataset, and how is the move chosen?
I've been doing some research on the principles behind AlphaZero.
Especially this cheat sheet (1) and this implementation (2) (in Connect 4) were very useful.
Yet, I still have two important questions:...
3
votes
0answers
43 views
How to deal with nonstationary rewards in asymmetric self-play reinforcement learning?
Suppose we're training two agents to play an asymmetric game from scratch using self play (like Zerg vs. Protoss in Starcraft). During training one of the agents can become stronger (discover a good ...
1
vote
1answer
133 views
What will Q-values look like in self-play tic-tac-toe?
This corresponds to Exercise 1.1 of RLBook, and a discussion followed from here.
Considering two reward schemes-
Win = +1, Draw = 0, Loss = -1
Win = +1, Draw or Loss = 0
Can we say something about ...
2
votes
1answer
297 views
Is Python and a single computer sufficient to implement and train an RL-based agent for a turn-based war game? [closed]
I have a steady hex-map and turn-based wargame featuring WWII carrier battles. I would like to improve the given AI part of the game using reinforcement learning.
I have a bunch of noob questions.
Is ...
1
vote
1answer
101 views
How can I oppose two AI agents with keras / tensoflow?
I am trying to use tensorflow / keras to play a text based game. The game opposes two players that play by answering questions by choosing an answer among the proposed ones.
Game resembles this:
...
4
votes
2answers
2k views
Why does self-playing TicTacToe not become perfect?
I trained a DQN that learns TicTacToe 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) against ...
3
votes
2answers
546 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 ...
