Avoiding Parameter Overfitting in a Monte Carlo Approach to Real-Time Strategy Games
نویسنده
چکیده
This project examines overfitting and generalization error with Monte Carlo Tree Search in the real-time strategy video game StarCraft and provides a basis for evaluating the specific scenarios of StarCraft based on their estimated generalization error. How can we tell if we are overfitting the input parameters to specific scenarios in StarCraft? How well does a specific scenario of StarCraft generalize to the entire game?
منابع مشابه
Robust Opponent Modeling in Real-Time Strategy Games using Bayesian Networks
Opponent modeling is a key challenge in Real-Time Strategy (RTS) games as the environment is adversarial in these games, and the player cannot predict the future actions of her opponent. Additionally, the environment is partially observable due to the fog of war. In this paper, we propose an opponent model which is robust to the observation noise existing due to the fog of war. In order to cope...
متن کاملGame-Tree Search over High-Level Game States in RTS Games
From an AI point of view, Real-Time Strategy (RTS) games are hard because they have enormous state spaces, they are real-time and partially observable. In this paper, we present an approach to deploy gametree search in RTS games by using game state abstraction. We propose a high-level abstract representation of the game state, that significantly reduces the branching factor when used for game-t...
متن کاملHigh-Level Representations for Game-Tree Search in RTS Games
From an AI point of view, Real-Time Strategy (RTS) games are hard because they have enormous state spaces, they are real-time and partially observable. In this paper, we explore an approach to deploy gametree search in RTS games by using game state abstraction, and explore the effect of using different abstractions over the game state. Different abstractions capture different parts of the game ...
متن کاملHigh-level Representations for Game-Tree Search in RTS Games
From an AI point of view, Real-Time Strategy (RTS) games are hard because they have enormous state spaces, they are real-time and partially observable. In this paper, we explore an approach to deploy gametree search in RTS games by using game state abstraction, and explore the effect of using different abstractions over the game state. Different abstractions capture different parts of the game ...
متن کاملUCT for Tactical Assault Planning in Real-Time Strategy Games
We consider the problem of tactical assault planning in real-time strategy games where a team of friendly agents must launch an assault on an enemy. This problem offers many challenges including a highly dynamic and uncertain environment, multiple agents, durative actions, numeric attributes, and different optimization objectives. While the dynamics of this problem are quite complex, it is ofte...
متن کامل