We’re excited to announce a **beta-version** of a brand-new type of ML competition called Simulations. In Simulation Competitions, you’ll compete against a set of rules, rather than against an evaluation metric. To enter, [accept the rules](/c/connectx/rules) and create a python submission file that can “play” against a computer, or another user.


## The Challenge
![“ConnectX”](https://storage.googleapis.com/kaggle-media/competitions/ConnectX/Walter's%20image.png)
In this game, your objective is to get a certain number of your checkers in a row horizontally, vertically, or diagonally on the game board before your opponent. When it's your turn, you “drop” one of your checkers into one of the columns at the top of the board. Then, let your opponent take their turn. This means each move may be trying to either win for you, or trying to stop your opponent from winning. The default number is four-in-a-row, but we’ll have other options to come soon.
## Background History

For the past 10 years, our competitions have been mostly focused on supervised machine learning. The field has grown, and we want to continue to provide the data science community cutting-edge opportunities to challenge themselves and grow their skills.

So, what’s next? Reinforcement learning is clearly a crucial piece in the next wave of data science learning. We hope that Simulation Competitions will provide the opportunity for Kagglers to practice and hone this burgeoning skill.

## How is this Competition Different?

Instead of submitting a CSV file, or a Kaggle Notebook, you will submit a Python .py file (more submission options are in development). You’ll also notice that the leaderboard is not based on how accurate your model is but rather how well you’ve performed against other users. See [Evaluation](/c/connectx/overview/evaluation) for more details.

## We’d Love Your Feedback

This competition is a low-stakes, trial-run introduction. We’re considering this a beta launch – there are complicated new mechanics in play and we’re still working on refining the process. We’d love your help testing the experience and want to hear your feedback.

Please note that we may make changes throughout the competition that could include things like resetting the leaderboard, invalidating episodes, making changes to the interface, or changing the environment configuration (e.g. modifying the number of columns, rows, or tokens in a row required to win, etc).