Abstract
Reinforcement learning is a machine learning technique that makes a decision based on a sequence of actions. This allows changing a game agent’s behavior through feedback, such as rewards or penalties for their actions. Recent work has been demonstrating the use of reinforcement learning to train agents capable of playing electronic games and obtain scores even higher than professional human players. These intelligent agents can also assume other roles, such as creating more complex challenges to players, improving the ambiance of more complex interactive games and even testing the behavior of players when the game is in development. Some literature has been using a deep learning technique to process an image of the game. This is known as the deep Q network and is used to create an intermediate representation and then process it by layers of neural network. These layers are capable of mapping game situations into actions that aim to maximize a reward over time. However, this method is not feasible in modern games, rendered in high resolution with an increasing frame rate. In addition, this method does not work for training agents who are not shown on the screen. In this work we propose a reinforcement learning pipeline based on neural networks, whose input is metadata, selected directly in the game state, and the actions are mapped directly into high-level actions by the agent. We propose this architecture for a tower defense player agent, a real time strategy game whose agent is not represented on the screen directly.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Justesen, N., Bontrager, P., Togelius, J., Risi, S.: Deep Learning for Video Game Playing. arxiv (2017). https://arxiv.org/pdf/1708.07902.pdf
Peng, P., et al.: Multiagent Bidirectionally-Coordinated Nets for Learning to Play StarCraft Combat Games. CoRR (2017). http://arxiv.org/abs/1703.10069
Gym library. https://gym.openai.com/. Accessed 16 May 2020
Deep Q-Learning with Keras and Gym. https://keon.github.io/deep-q-learning/. Accessed 20 May 2020
How to teach AI to play Games: Deep Reinforcement Learning. https://towardsdatascience.com/how-to-teach-an-ai-to-play-games-deep-reinforcement-learning-28f9b920440a. Accessed 12 May 2020
Advanced DQNs: Playing Pac-man with Deep Reinforcement Learning. https://towardsdatascience.com/advanced-dqns-playing-pac-man-with-deep-reinforcement-learning-3bd99e0814. Accessed 25 Apr 2020
How to match DeepMind’s Deep Q-Learning score in Breakout. https://towardsdatascience.com/tutorial-double-deep-q-learning-with-dueling-network-architectures-4c1b3fb7f756. Accessed 25 Oct 2019
Justesen, N., Risi, S.: Learning Macromanagement in StarCraft from Replays using Deep Learning. CoRR (2017). https://arxiv.org/pdf/1707.03743.pdf
My first experience with deep reinforcement learning. https://medium.com/ai-society/my-first-experience-with-deep-reinforcement-learning-1743594f0361. Accessed 21 Feb 2020
Mnih, V., et al.: Playing Atari with Deep Reinforcement Learning. arxiv (2013). https://arxiv.org/pdf/1312.5602v1.pdf
Usunier, N., Synnaeve, G., Lin, Z., Chintala, S.: Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks. CoRR (2016). https://arxiv.org/pdf/1609.02993.pdf
Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: A Brief Survey of Deep Reinforcement Learning. arxiv (2017). https://arxiv.org/pdf/1708.05866.pdf
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529 (2015)
Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)
Acknowledgments
This work has been supported by FCT – Fundação para a Ciência e Tecnologia within the Project Scope: UIDB/05757/2020.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Dias, A., Foleiss, J., Lopes, R.P. (2022). Reinforcement Learning in Tower Defense. In: Barbedo, I., Barroso, B., Legerén, B., Roque, L., Sousa, J.P. (eds) Videogame Sciences and Arts. VJ 2020. Communications in Computer and Information Science, vol 1531. Springer, Cham. https://doi.org/10.1007/978-3-030-95305-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-95305-8_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95304-1
Online ISBN: 978-3-030-95305-8
eBook Packages: Computer ScienceComputer Science (R0)