⚡ Updated Starter Kit: a full DQN baseline you can submit out of the box!

:memo: TL:DR: We have updated the starter kit: it is now a full RL baseline that you can easily train and submit out of the box! https://gitlab.aicrowd.com/flatland/neurips2020-flatland-starter-kit

Making your first submission can be challenging: you need to get familiar with the Flatland APIs, discover the submission process, write out all your dependencies in the apt.txt and environment.yml files…
This can take a few tries to get right, and is not particularly satisfying!

To help with this process, we have updated the starter kit. It is now a full PyTorch-powered DQN baseline that you can submit right away.

:robot: Trainable for free on Colab

You can train a full agent using the starter kit running everything on Colab. Colab is a free notebook service that allows you to run code in the cloud for free. You can even use GPUs if you want to experiment with larger networks!

:nut_and_bolt: Easy to tweak and extend

The training script exposes many parameters to quickly test hypotheses:

  • Epsilon decay (start, end, and decay rate)
  • Buffer size and min size before training starts
  • Learning rate, gamma, tau…

See here for the full list of command line parameters: https://gitlab.aicrowd.com/flatland/neurips2020-flatland-starter-kit#sample-training-usage

:twisted_rightwards_arrows: Easy hyper-parameter tuning

You can use the (free) Weight & Biases service to log experiment results and to automate hyperparameter sweeps:

Sample report: https://wandb.ai/masterscrat/flatland-examples-reinforcement_learning/reports/Flatland-Examples--VmlldzoxNDI2MTA

Documentation: https://docs.wandb.com/sweeps

:white_check_mark: Provided checkpoint

The starter kit comes with a sample checkpoint which should allow you to reach ~50 points on the leaderboard straight away. As of right now, this would put you in the top 15!

:file_cabinet:Old starter kit

The previous version is available in the old-starter-kit branch as a reference: