# 🚂 Flatland Baselines

This repository contains reinforcement learning baselines for the [NeurIPS 2020 Flatland Challenge](https://www.aicrowd.com/challenges/neurips-2020-flatland-challenge/).

## Provided baselines

### RL Methods

- Double Dueling DQN 
- Ape-X
- PPO
- CCPPO
- Pure Imitation Learning: MARWIL
- Mixed IL/RL: DQfD 

### Custom observations

- Density observations
- Local conflict observations

### Tricks

- Action skipping
- Action masking

## Organisation

Experiments consist of one or many RLlib YAML config files alongside a MARKDOWN file containing results, plots and a detailed description of the methodology.

All files are stored in a experiment folder under `experiments/<env-name>/<experiment-name>`.

- [Tree observations w/ fully connected network](experiments/flatland_random_sparse_small/tree_obs_fc_net)
- [Global observations w/ convnet](experiments/flatland_random_sparse_small/global_obs_conv_net)

## Setup

The setup uses conda, [install it](https://www.anaconda.com/products/individual) if necessary.

```
# with GPU support:
conda env create -f environment-gpu.yml
conda activate flatland-baseline-gpu-env

# or, without GPU support:
conda env create -f environment-cpu.yml
conda activate flatland-baseline-cpu-env
```

## Usage

Training example:

`python ./train.py -f experiments/flatland_random_sparse_small/global_obs_conv_net/ppo.yaml`

Evaluation example:

`python ./rollout.py /tmp/ray/checkpoint_dir/checkpoint-0 --run PPO --no-render
        --config '{"env_config": {"test": true}}' --episodes 1000 --out rollouts.pkl`

Note that `-f` overrides all other trial-specific command-line options.

## Notes

- The basic structure of this repository is adapted from [https://github.com/spMohanty/rl-experiments/](https://github.com/spMohanty/rl-experiments/)