Corpus ID: 202614720

Project Proposal : Deep Learning AI for Racing Games

  title={Project Proposal : Deep Learning AI for Racing Games},
  author={Emilio Capo},
  • Emilio Capo
  • Published 2018
  • This is especially true in racing games, where AI is typically provided with a simplified physics and vehicle model with respect to the ones the players is subject to. This leads to noticeable incoherencies, such as opponents overcoming physical limitations under the same conditions as the player. Moreover, these agents also struggle with handling adversarial contexts with different computer-controlled cars, which are usually solved through heuristics. 

    Figures from this paper


    End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning
    • 26
    • PDF
    DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
    • 1,003
    • PDF
    Asynchronous Methods for Deep Reinforcement Learning
    • 3,786
    • PDF
    Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning
    • 20
    • PDF
    Evolving deep unsupervised convolutional networks for vision-based reinforcement learning
    • 91
    • PDF
    Continuous control with deep reinforcement learning
    • arXiv preprint arXiv:1509.02971,
    • 2015