An Oracle and Observations for the OpenAI Gym / ALE Freeway Environment
This work is incremental, as it focuses on improving evaluation tools for a specific domain (reinforcement learning in the OpenAI Gym Freeway environment) rather than advancing general AI methods.
The authors tackled the problem of evaluating reinforcement learning solutions in the Freeway-ram-v0 environment by developing an oracle to play the game, providing baselines and optimal scenarios for training and testing AI agents.
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.