Umělý hráč pro Angry Birds

Abstract

Angry Birds is a popular video game, in which the player is provided with a sequence of birds to shoot from a slingshot. The task of the game is to kill all green pigs with maximum possible score. Angry Birds appears to be a difficult task to solve for artificially intelligent agents due to the sequential decision-making, nondeterministic game environment, enormous state and action spaces and requirement to differentiate between multiple birds, their abilities and optimum tapping times. In this thesis, we are presenting several different techniques suitable for the implementation of artificial Angry Birds agent. First, we will show how limited Breath First Search can be used to estimate potentially good shooting points. After that we will discover how reinforcement learning can be applied to the Angry Birds game. Lastly, we will apply Deep reinforcement learning to Angry Birds game by implementing Double Dueling Deep Q- networks. One of our main goals was to build an agent that is able to compete in AIBirds competition and with humans on the game's first 21 levels. In order to do so, we have collected a dataset of game frames that we used to train our agent. We evaluate our agents using results of the previous participants of AIBirds competition and results of volunteer human players.