Solving JumpIN’ Using Zero-Dependency Reinforcement Learning (Student Abstract)


  • Rachel Ostic University of Ottawa
  • Oliver Benning University of Ottawa
  • Patrick Boily University of Ottawa Data Action Lab, Ottawa Idlewyld Analytics and Consulting Services, Wakefield


Reinforcement Learning, Single-player Game, Q-learning, JumpIN'


Reinforcement learning seeks to teach agents to solve problems using numerical rewards as feedback. This makes it possible to incentivize actions that maximize returns despite having no initial strategy or knowledge of their environment. We implement a zero-external-dependency Q-learning algorithm using Python to optimally solve the single-player game JumpIn’ from SmartGames. We focus on interpretability of the model using Q-table parsing, and transferability to other games through a modular code structure. We observe rapid performance gains using our backtracking update algorithm.




How to Cite

Ostic, R., Benning, O., & Boily, P. (2021). Solving JumpIN’ Using Zero-Dependency Reinforcement Learning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15861-15862. Retrieved from



AAAI Student Abstract and Poster Program