Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/81558
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Justesen, Niels | - |
dc.contributor.author | Rodriguez Torrado, Ruben | - |
dc.contributor.author | Bontrager, Philip | - |
dc.contributor.author | Khalifa, Ahmed | - |
dc.contributor.author | Togelius, Julian | - |
dc.contributor.author | Risi, Sebastian | - |
dc.date.accessioned | 2021-09-28T10:14:50Z | - |
dc.date.available | 2021-09-28T10:14:50Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Justesen, N., Rodriguez Torrado, R., Bontrager, P., Khalifa, A., Togelius, J., & Risi, S. (2018). Illuminating generalization in deep reinforcement learning through procedural level generation. NeurIPS Deep RL Workshop 2018, Montreal. | en_GB |
dc.identifier.uri | https://www.um.edu.mt/library/oar/handle/123456789/81558 | - |
dc.description.abstract | Deep reinforcement learning (RL) has shown impressive results in a variety of domains, learning directly from high-dimensional sensory streams. However, when neural networks are trained in a fixed environment, such as a single level in a video game, they will usually overfit and fail to generalize to new levels. When RL models overfit, even slight modifications to the environment can result in poor agent performance. This paper explores how procedurally generated levels during training can increase generality. We show that for some games procedural level generation enables generalization to new levels within the same distribution. Additionally, it is possible to achieve better performance with less data by manipulating the difficulty of the levels in response to the performance of the agent. The generality of the learned behaviors is also evaluated on a set of human-designed levels. The results suggest that the ability to generalize to human-designed levels highly depends on the design of the level generators. We apply dimensionality reduction and clustering techniques to visualize the generators’ distributions of levels and analyze to what degree they can produce levels similar to those designed by a human. | en_GB |
dc.language.iso | en | en_GB |
dc.publisher | NeurIPS Deep RL Workshop | en_GB |
dc.rights | info:eu-repo/semantics/openAccess | en_GB |
dc.subject | Artificial intelligence | en_GB |
dc.subject | Machine learning | en_GB |
dc.subject | Reinforcement learning | en_GB |
dc.subject | Computer games -- Design | en_GB |
dc.subject | Level design (Computer science) | en_GB |
dc.title | Illuminating generalization in deep reinforcement learning through procedural level generation | en_GB |
dc.type | conferenceObject | en_GB |
dc.rights.holder | The copyright of this work belongs to the author(s)/publisher. The rights of this work are as defined by the appropriate Copyright Legislation or as modified by any successive legislation. Users may access this work and can make use of the information contained in accordance with the Copyright Legislation provided that the author must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the prior permission of the copyright holder. | en_GB |
dc.bibliographicCitation.conferencename | NeurIPS Deep RL Workshop 2018 | en_GB |
dc.bibliographicCitation.conferenceplace | Montreal, Canada, 07/12/2018 | en_GB |
dc.description.reviewed | peer-reviewed | en_GB |
Appears in Collections: | Scholarly Works - InsDG |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Illuminating_generalization_in_deep_reinforcement_learning_through_procedural_level_generation_2018.pdf | 987.1 kB | Adobe PDF | View/Open |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.