James S. Plank, Catherine D. Schuman and Robert M. Patton

September, 2021

Published on arXiv.

https://arxiv.org/abs/2109.01220

View Article

Abstract

The OpenAI Gym project contains hundreds of control problems whose goal is to provide a testbed for reinforcement learning algorithms. One such problem is Freeway-ram-v0, where the observations presented to the agent are 128 bytes of RAM. While the goals of the project are for non-expert AI agents to solve the control problems with general training, in this work, we seek to learn more about the problem, so that we can better evaluate solutions. In particular, we develop on oracle to play the game, so that we may have baselines for success. We present details of the oracle, plus optimal game-playing situations that can be used for training and testing AI agents.

Citation Information

Text

title        An Oracle and Observations for the OpenAI Gym / ALE Freeway Environment
author       James S. Plank and Catherine D. Schuman and Robert M. Patton
howpublished arXiv:2109.01220
url          https://arxiv.org/abs/2109.01220
eprint       2109.01220 
year         2021

Bibtex

@MISC{psp:21:aoo,
    title = "An Oracle and Observations for the OpenAI Gym / ALE Freeway Environment",
    author = "James S. Plank and Catherine D. Schuman and Robert M. Patton",
    howpublished = "arXiv:2109.01220",
    url = "https://arxiv.org/abs/2109.01220",
    eprint = "2109.01220 ",
    year = "2021"
}