Discrete-World

Files:

1. agent.py : script to define agent and generate a policy
2. design_obstacles.py : use PyGame to design goals and obstacles via point-and-click
3. grid.py : define the grid-world and optionally, its rewards
4. main.py : main driver script that shows an example
5. plotting.py : generate plots for the reward and grid-world

---

If you use this grid-world setup, please consider citing:

@misc{puranic_dw,
author = "Aniruddh G. Puranic and Anand Balakrishnan",
title  = "Reinforcement Learning Environment for Multiple Tasks",
year   = 2020,
url    = {https://github.com/CPS-VIDA/discrete-world} 
}

---

This environment was used to generate plots for experiments in the paper Learning from Demonstrations using Signal Temporal Logic.