Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning

被引:3
|
作者
Muller-Brockhausen, Matthias [1 ]
Preuss, Mike [1 ]
Plaat, Aske [1 ]
机构
[1] Leiden Univ, Leiden Inst Adv Comp Sci, Leiden, Netherlands
关键词
Transfer; Reinforcement Learning; Benchmarks; Procedural Content Generation; FRAMEWORK; AI;
D O I
10.1109/COG52621.2021.9619000
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The idea of transfer in reinforcement learning (TRL) is intriguing: being able to transfer knowledge from one problem to another problem without learning everything from scratch. This promises quicker learning and learning more complex methods. To gain an insight into the field and to detect emerging trends, we performed a database search. We note a surprisingly late adoption of deep learning that starts in 2018. The introduction of deep learning has not yet solved the greatest challenge of TRL: generalization. Transfer between different domains works well when domains have strong similarities (e.g. MountainCar to Cartpole), and most TRL publications focus on different tasks within the same domain that have few differences. Most TRL applications we encountered compare their improvements against self-defined baselines, and the field is still missing unified benchmarks. We consider this to be a disappointing situation. For the future, we note that: (1) A clear measure of task similarity is needed. (2) Generalization needs to improve. Promising approaches merge deep learning with planning via MCTS or introduce memory through LSTMs. (3) The lack of benchmarking tools will be remedied to enable meaningful comparison and measure progress. Already Alchemy and Meta-World are emerging as interesting benchmark suites. We note that another development, the increase in procedural content generation (PCG), can improve both benchmarking and generalization in TRL.
引用
收藏
页码:924 / 931
页数:8
相关论文
共 50 条
  • [1] Adversarial Reinforcement Learning for Procedural Content Generation
    Gisslen, Linus
    Eakins, Andy
    Gordillo, Camilo
    Bergdahl, Joakim
    Tollmar, Konrad
    2021 IEEE CONFERENCE ON GAMES (COG), 2021, : 9 - 16
  • [2] Intrinsically Motivated Reinforcement Learning: A Promising Framework for Procedural Content Generation
    Shaker, Noor
    2016 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND GAMES (CIG), 2016,
  • [3] Procedural Content Generation using Reinforcement Learning and Entropy Measure as Feedback
    Moreira Dutra, Paulo Vinicius
    Villela, Saulo Moraes
    Neto, Raul Fonseca
    2022 21ST BRAZILIAN SYMPOSIUM ON COMPUTER GAMES AND DIGITAL ENTERTAINMENT (SBGAMES), 2022, : 7 - 12
  • [4] Procedural Material Generation with Reinforcement Learning
    Li, Beichen
    Hu, Yiwei
    Guerrero, Paul
    Hasan, Milos
    Shi, Liang
    Deschaintre, Valentin
    Matusik, Wojciech
    ACM TRANSACTIONS ON GRAPHICS, 2024, 43 (06):
  • [5] Leveraging Procedural Generation to Benchmark Reinforcement Learning
    Cobbe, Karl
    Hesse, Christopher
    Hilton, Jacob
    Schulman, John
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [6] Leveraging Procedural Generation to Benchmark Reinforcement Learning
    Cobbe, Karl
    Hesse, Christopher
    Hilton, Jacob
    Schulman, John
    25TH AMERICAS CONFERENCE ON INFORMATION SYSTEMS (AMCIS 2019), 2019,
  • [7] Deep Reinforcement Learning for Procedural Content Generation of 3D Virtual Environments
    Lopez, Christian E.
    Cunningham, James
    Ashour, Omar
    Tucker, Conrad S.
    JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING, 2020, 20 (05)
  • [8] A mixed-initiative design framework for procedural content generation using reinforcement learning
    Dutra, Paulo Vinicius Moreira
    Villela, Saulo Moraes
    Neto, Raul Fonseca
    ENTERTAINMENT COMPUTING, 2025, 52
  • [9] Deep learning for procedural content generation
    Liu, Jialin
    Snodgrass, Sam
    Khalifa, Ahmed
    Risi, Sebastian
    Yannakakis, Georgios N.
    Togelius, Julian
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (01): : 19 - 37
  • [10] Deep learning for procedural content generation
    Jialin Liu
    Sam Snodgrass
    Ahmed Khalifa
    Sebastian Risi
    Georgios N. Yannakakis
    Julian Togelius
    Neural Computing and Applications, 2021, 33 : 19 - 37