Solving JumpIN' with reinforcement learning

Last updated on Feb 16, 2021
Schematic by Rachel Ostic based on SmartGames board design

Project to learn more about Python and reinforcement learning applied to the single-player game JumpIN'. The solver trains on puzzles and, through Q-learning feedback, more efficient solutions are reinforced.

JumpIN' Reinforcement learning Q-learning Single-player game Python
Rachel Ostic
Rachel Ostic
Data scientist

I’m fascinated by data analysis and how it combines abstract thinking with real world problems, and I am starting to fuse this interest with programming both personally and at work.

Publications

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

Reinforcement learning seeks to teach agents to solve problems using numerical rewards as feedback. This makes it possible to …
Project Link

Talks

Solving JumpIN’ Using Zero-Dependency Reinforcement Learning

Poster presentation in the Student Abstract category on using reinforcement learning to solve JumpIN', a single-player game.
Feb 6, 2021 Virtual
PDF Project