A Benchmark Environment for Offline Reinforcement Learning in Racing Games

TL;DR

This paper introduces OfflineMania, a new Unity-based racing environment inspired by TrackMania, designed to facilitate offline reinforcement learning research with diverse datasets and baseline comparisons.

Contribution

The paper presents OfflineMania, a novel benchmarking environment for offline RL in racing games, including diverse datasets and baseline algorithms for evaluation.

Findings

OfflineMania provides a challenging testbed for offline RL algorithms.

Diverse datasets enable comprehensive assessment of algorithm performance.

Baseline results establish reference points for future research.

Abstract

Offline Reinforcement Learning (ORL) is a promising approach to reduce the high sample complexity of traditional Reinforcement Learning (RL) by eliminating the need for continuous environmental interactions. ORL exploits a dataset of pre-collected transitions and thus expands the range of application of RL to tasks in which the excessive environment queries increase training time and decrease efficiency, such as in modern AAA games. This paper introduces OfflineMania a novel environment for ORL research. It is inspired by the iconic TrackMania series and developed using the Unity 3D game engine. The environment simulates a single-agent racing game in which the objective is to complete the track through optimal navigation. We provide a variety of datasets to assess ORL performance. These datasets, created from policies of varying ability and in different sizes, aim to offer a challenging testbed for algorithm development and evaluation. We further establish a set of baselines for a range of Online RL, ORL, and hybrid Offline to Online RL approaches using our environment.