Questions tagged [imperfect-information]
Use for models where all previous actions/states are not known by participants. Distinct from Incomplete Information. Imperfect Information may be a subset of the blanket term "Hidden Information"
10
questions
0
votes
0
answers
64
views
Why do policy gradient methods not work for imperfect information games?
I've heard before that policy gradient and Q-learning approaches fail on games of imperfect information. I was watching this video (starting at 23:45) about the Player of Games AI, but I couldn't ...
- 125
4
votes
1
answer
464
views
Why multiplayer, imperfect information, trick-taking card games are hard for AI?
AI reached a super-human level in many complex games such as Chess, Go ,Texas hold’em Poker, Dota2 and StarCarft2. However it still did not reach this level in trick-taking card games.
Why there is no ...
- 405
6
votes
2
answers
614
views
Are perfect and imperfect information games modelled as fully and partially observable environments, respectively?
In perfect information games, the agent can see all the moves performed in the past. Besides, it can observe the next action that will be put into practice by the opponent.
In this case, can we say ...
- 161
3
votes
0
answers
355
views
What is the state of the art AI training technique for imperfect information 2 player turn based games?
As far as I can tell (correct me if I'm wrong), Alphazero (with MCTS and neural network heuristic function RL) is the state of the art training method for turn based, deterministic, perfect ...
- 161
1
vote
0
answers
60
views
What to study for this simple poker game?
I'm a programmer with a background in mathematics, but I have no experience whatsoever with artificial intelligence/neural networks. I'd like to study it as a hobby, and my goal for now is to solve ...
- 11
3
votes
0
answers
445
views
How do to mitigate or design out hidden feedback loops when designing ML systems?
Two months ago, I've found myself working on a churn detection problem which can be briefly described as follows:
Assume the current date is N
Use customer behavior for N-1,..N-x dates to develop ...
- 73
6
votes
1
answer
5k
views
Why most imperfect information games usually use non machine learning AI?
To provide a bit of context, I'm a software engineer & game enthusiast (card games, especially). The thing is I've always been interested in AI oriented to games. In college, I programmed my own ...
2
votes
1
answer
1k
views
How to use DQN to handle an imperfect but complete information game?
I'm currently having troubles to win against a random bot playing the Schieber Jass game. It is a imperfect card information game. (famous in switzerland https://www.schieber.ch/)
The environement I'...
- 81
7
votes
2
answers
485
views
In this implementation of the Information Set Monte Carlo Tree Search, why can't the players see the cards of each other?
After reading this paper about Monte Carlo methods for imperfect information games with elements of uncertainty, I couldn't understand the application of the determinization step in the author's ...
- 71
8
votes
1
answer
304
views
How powerful is the machine that beat the poker professional players recently?
How powerful is the machine that beat the poker professional players recently (DeepStack)?
- 89