Learning to play donkey kong using neural networks and reinforcement learning

Paul Ozkohen, Jelle Visser, Martijn van Otterlo, Marco Wiering*

*Corresponding author for this work

    Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review


    Neural networks and reinforcement learning have successfully been applied to various games, such as Ms. Pacman and Go. We combine multilayer perceptrons and a class of reinforcement learning algorithms known as actor-critic to learn to play the arcade classic Donkey Kong. Two neural networks are used in this study: the actor and the critic. The actor learns to select the best action given the game state; the critic tries to learn the value of being in a certain state. First, a base game-playing performance is obtained by learning from demonstration, where data is obtained from human players. After this off-line training phase we further improve the base performance using feedback from the critic. The critic gives feedback by comparing the value of the state before and after taking the action. Results show that an agent pre-trained on demonstration data is able to achieve a good baseline performance. Applying actor-critic methods, however, does usually not improve performance, in many cases even decreases it. Possible reasons include the game not fully being Markovian and other issues.

    Original languageEnglish
    Title of host publicationArtificial Intelligence - 29th Benelux Conference, BNAIC 2017, Revised Selected Papers
    Number of pages16
    ISBN (Print)9783319768915
    Publication statusPublished - Feb 2018
    Event29th Benelux Conference on Artificial Intelligence, BNAIC 2017 - Groningen, Netherlands
    Duration: 8 Nov 20179 Nov 2017

    Publication series

    NameCommunications in Computer and Information Science
    ISSN (Print)1865-0929


    Conference29th Benelux Conference on Artificial Intelligence, BNAIC 2017


    • Actor-critic
    • Donkey Kong
    • Games
    • Machine learning
    • Neural networks
    • Platformer
    • Reinforcement learning


    Dive into the research topics of 'Learning to play donkey kong using neural networks and reinforcement learning'. Together they form a unique fingerprint.

    Cite this