Learning a Super Mario controller from examples of human play | IEEE Conference Publication | IEEE Xplore

Learning a Super Mario controller from examples of human play


Abstract:

Imitating human-like behaviour in action games is a challenging but intriguing task in Artificial Intelligence research, with various strategies being employed to solve t...Show More

Abstract:

Imitating human-like behaviour in action games is a challenging but intriguing task in Artificial Intelligence research, with various strategies being employed to solve the human-like imitation problem. In this research we consider learning human-like behaviour via Markov decision processes without being explicitly given a reward function, and learning to perform the task by observing expert's demonstration. Individual players often have characteristic styles when playing the game, and this method attempts to find the behaviours which make them unique. During play sessions of Super Mario we calculate player's behaviour policies and reward functions by applying inverse reinforcement learning to the player's actions in game. We conduct an online questionnaire which displays two video clips, where one is played by a human expert and the other is played by the designed controller based on the player's policy. We demonstrate that by using apprenticeship learning via Inverse Reinforcement Learning, we are able to get an optimal policy which yields performance close to that of an human expert playing the game, at least under specific conditions.
Date of Conference: 06-11 July 2014
Date Added to IEEE Xplore: 22 September 2014
ISBN Information:

ISSN Information:

Conference Location: Beijing, China
Citations are not available for this document.

I. Introduction

The game industry has been rapidly expanding for the past few decades and it is the fastest-growing component of the international media sector. It has been devoting considerable resources to design highly sophisticated graphical content and challenging and believable Artificial Intelligence (AI). Various artificial intelligence methods have been employed in modern video games to engage players longer, game agents built with human-like behaviour and cooperation, which raise the players' emotional involvement and increase immersion in the game simulation.

Cites in Papers - |

Cites in Papers - IEEE (5)

Select All
1.
Ye Rin Kim, Hyun Duck Choi, "CNN-based Apprenticeship Learning for Inverse Reinforcement Learning", 2024 24th International Conference on Control, Automation and Systems (ICCAS), pp.73-78, 2024.
2.
Jianian Zheng, Huiyi Cao, Diliang Chen, Rahila Ansari, Kuo-Chung Chu, Ming-Chun Huang, "Designing Deep Reinforcement Learning Systems for Musculoskeletal Modeling and Locomotion Analysis Using Wearable Sensor Feedback", IEEE Sensors Journal, vol.20, no.16, pp.9274-9282, 2020.
3.
Sang-Hyun Lee, Seung-Woo Seo, "A learning-based framework for handling dilemmas in urban automated driving", 2017 IEEE International Conference on Robotics and Automation (ICRA), pp.1436-1442, 2017.
4.
Maxim Mozgovoy, Marina Purgina, Iskander Umarov, "Believable self-learning AI for world of tennis", 2016 IEEE Conference on Computational Intelligence and Games (CIG), pp.1-7, 2016.
5.
Jayden Ivanovo, William L. Raffe, Fabio Zambetta, Xiaodong Li, "Combining Monte Carlo tree search and apprenticeship learning for capture the flag", 2015 IEEE Conference on Computational Intelligence and Games (CIG), pp.154-161, 2015.

Cites in Papers - Other Publishers (7)

1.
Yuchen Wang, Mitsuhiro Hayashibe, Dai Owaki, "Data-Driven Policy Learning Methods from Biological Behavior: A Systematic Review", Applied Sciences, vol.14, no.10, pp.4038, 2024.
2.
Pedro M. Fernandes, Manuel Lopes, Rui Prada, "Data Driven Agents for\xa0User Experience Testing", Videogame Sciences and Arts, vol.1984, pp.3, 2024.
3.
Jessica Rivera-Villicana, Fabio Zambetta, James Harland, Marsha Berry, "Exploring Apprenticeship Learning for Player Modelling in Interactive Narratives", Extended Abstracts of the Annual Symposium on Computer-Human Interaction in Play Companion Extended Abstracts, pp.645, 2019.
4.
Nic Velissaris, Jessica Rivera-Villicana, "Towards Intelligent Interactive Theatre: Drama Management as a Way of Handling Performance", Interactive Storytelling, vol.11869, pp.233, 2019.
5.
Evan C. Sheffield, Michael D. Shah, "Dungeon Digger", Proceedings of the 2018 Annual Symposium on Computer-Human Interaction in Play Companion Extended Abstracts, pp.603, 2018.
6.
Shaghayegh Roohi, Jari Takatalo, Christian Guckelsberger, Perttu Hämäläinen, "Review of Intrinsic Motivation in Simulation-based Game Testing", Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, pp.1, 2018.
7.
Ahmed Hussein, Mohamed Medhat Gaber, Eyad Elyan, Chrisina Jayne, "Imitation Learning", ACM Computing Surveys, vol.50, no.2, pp.1, 2017.

References

References is not available for this document.