An Oracle and Observations for the OpenAI Gym / ALE Freeway Environment

TL;DR

This paper introduces an oracle for the Freeway RAM environment in OpenAI Gym, providing optimal gameplay benchmarks to better evaluate reinforcement learning agents in this control problem.

Contribution

It develops an oracle for Freeway-ram-v0 and identifies optimal game states for training and testing AI agents, enhancing evaluation methods.

Findings

An oracle for Freeway-ram-v0 is constructed.

Optimal game-playing situations are identified.

The oracle serves as a baseline for reinforcement learning performance.

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.