|
|
Deep Neural Networks for Reinforcement Learning in Real-Time Strategy
Barilla, Marco ; Dobeš, Petr (referee) ; Kolář, Martin (advisor)
Machine learning is one of the fastest growing branches of modern science. It is a subfield of artificial intelligence research that is interested the problem of making computers help us solve complex modern problems. Games play an important role in this field because they represent the perfect environment for testing of new approaches and benchmarking against human performance. Starcraft 2 is currently in the spotlight, thanks to its broad playerbase and its complexity. The practical goal of this paper is to create an advantage actor critic agent that is able to operate in the environment of this game.
|
|
|
Machine Learning in Strategic Games
Vlček, Michael ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
Machine learning is spearheading progress for the field of artificial intelligence in terms of providing competition in strategy games to a human opponent, be it in a game of chess, Go or poker. A field of machine learning, which shows the most promising results in playing strategy games, is reinforcement learning. The next milestone for the current research lies in a computer game Starcraft II, which outgrows the previous ones in terms of complexity, and represents a potential new breakthrough in this field. The paper focuses on analysis of the problem, and suggests a solution incorporating a reinforcement learning algorithm A2C and hyperparameter optimization implementation PBT, which could mean a step forward for the current progress.
|
|
|
Reinforcement Learning for Bomberman Type Game
Adamčiak, Jakub ; Beran, Vítězslav (referee) ; Hradiš, Michal (advisor)
This bachelor's thesis aims to develop, implement and train reinforcement learning models for a Bomberman-type game. It is based on Bomberland environment from CoderOne. This environment was created for education and research in the field of artificial intelligence. In this thesis I tackle the settings and problems of implementing agent into the environment. I used 2 policies (MLP and CNN), 2 algorithms (PPO and A2C) and 5 setups of neural networks for feature extraction with the use of libraries stable baselines 3 and pytorch. Total training time resulted in 1207 real-world hours, 4168 computing hours and 271 milions of time steps. Although the training was not successful, this thesis shows the process of implementing a reinforcement learning model into a Gym environment.
|
|
|
Reinforcement Learning for Bomberman Type Game
Adamčiak, Jakub ; Beran, Vítězslav (referee) ; Hradiš, Michal (advisor)
This bachelor's thesis aims to develop, implement and train reinforcement learning models for a Bomberman-type game. It is based on Bomberland environment from CoderOne. This environment was created for education and research in the field of artificial intelligence. In this thesis I tackle the settings and problems of implementing agent into the environment. I used 2 policies (MLP and CNN), 2 algorithms (PPO and A2C) and 5 setups of neural networks for feature extraction with the use of libraries stable baselines 3 and pytorch. Total training time resulted in 1207 real-world hours, 4168 computing hours and 271 milions of time steps. Although the training was not successful, this thesis shows the process of implementing a reinforcement learning model into a Gym environment.
|
|
|
Deep Neural Networks for Reinforcement Learning in Real-Time Strategy
Barilla, Marco ; Dobeš, Petr (referee) ; Kolář, Martin (advisor)
Machine learning is one of the fastest growing branches of modern science. It is a subfield of artificial intelligence research that is interested the problem of making computers help us solve complex modern problems. Games play an important role in this field because they represent the perfect environment for testing of new approaches and benchmarking against human performance. Starcraft 2 is currently in the spotlight, thanks to its broad playerbase and its complexity. The practical goal of this paper is to create an advantage actor critic agent that is able to operate in the environment of this game.
|
|
|
Machine Learning in Strategic Games
Vlček, Michael ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
Machine learning is spearheading progress for the field of artificial intelligence in terms of providing competition in strategy games to a human opponent, be it in a game of chess, Go or poker. A field of machine learning, which shows the most promising results in playing strategy games, is reinforcement learning. The next milestone for the current research lies in a computer game Starcraft II, which outgrows the previous ones in terms of complexity, and represents a potential new breakthrough in this field. The paper focuses on analysis of the problem, and suggests a solution incorporating a reinforcement learning algorithm A2C and hyperparameter optimization implementation PBT, which could mean a step forward for the current progress.
|
guest ::
