8
votes
Accepted
Why most imperfect information games usually use non machine learning AI?
A heuristic search using MCTS + minimax + alphabeta pruning is a highly efficient AI planning process. What the AI techniques of reinforcement learning (RL) plus neural networks (NNs) typically add to ...
- 32.9k
3
votes
How to use DQN to handle an imperfect but complete information game?
Would it be helpful to use a LSTM and reduce the input state?
I'd bet, no. LSTM is more complicated and harder to learn, while the input is 4 * 9 * 36 bits is still rather limited.
However, you may ...
- 563
3
votes
How powerful is the machine that beat the poker professional players recently?
From the Deep Stack paper:
This seems to be for training:
For the turn network, ten million poker turn situations (from after the turn card is dealt) were generated and solved with 6,144 CPU cores ...
- 4,295
3
votes
Are perfect and imperfect information games modelled as fully and partially observable environments, respectively?
There is indeed a close parallel here, but the concepts are distinct. Every perfect information game is fully observable, but not every fully observable game is a game of perfect information.
A game ...
- 9,342
1
vote
Are perfect and imperfect information games modelled as fully and partially observable environments, respectively?
Not exactly, at least traditionally: in Game Theory, "imperfect information" is most often defined as agents having only partial information about the history of agents' actions, as you correctly ...
1
vote
In this implementation of the Information Set Monte Carlo Tree Search, why can't the players see the cards of each other?
MCTS only need to "see" states in respect of reward. All game mechanics is abstarcted away from MCTS and MCTS only access actions and rewards. MCTS player don't access states itself, it's only choose ...
- 725
1
vote
In this implementation of the Information Set Monte Carlo Tree Search, why can't the players see the cards of each other?
All the methods in the GameState class that is used to represent state, are stubs, and without these, the MCTS algorithm won't do anything at all. In particular, the DoMove method just changes who's ...
- 9,342
Only top scored, non community-wiki answers of a minimum length are eligible