Developing a fair and balanced baseball schedule is a challenging problem. This is because the appropriate balance between required and desired needs to be obtained while ensuring that these constraints are both applied and satisfied. Additionally, alternative measures need to be made to account for cases when certain combination of constraints applied together create an unsatisfactory schedule. This work addresses these limitations via first presenting a foundational framework for intelligent baseball scheduling that include the following.
1.Developed a Python-based constraint library that describes required constraints.
2.Modeled the incorporation of required constraints as a Markov decision process.
3.Developed a custom AIGym environment that demonstrates this process, where we also leverage state-of-the art operations research (OR) tools (e.g., Google OR tools).

Our results represented on the The High-A Central Baseball League is used as an example demonstration of our foundational framework, which can be used to build a reinforcement learning (or other machine learning frameworks) for robust baseball scheduling.

Team Members

[foreach 357]

• [if 397 not_equal=””][/if 397][395]

[/foreach 357]

Project Mentors, Sponsors, and Partners

• Antwan Clark

• Anton Dahbura

Course Faculty

[foreach 429]

• [if 433 not_equal=””][/if 433][431]

[/foreach 429]

Project Links

• Project Poster Image

Additional Project Information