Publikation
PGTG: Procedurally Generated Grid-Based Traffic Gym
Joshua Meyer; Felix Maurice Kuntz; Verena Wolf; Jörg Hoffmann; Timo P. Gros
In: Reinforcement Learning Journal (RLJ), Vol. 7, Pages 1-28, Manning College of Information and Computer Sciences, University of Massachusetts Amherst, 2026.
Zusammenfassung
We present Procedurally Generated Grid-Based Traffic Gym (PGTG), a Gymnasiumcompliant, feature-rich, extensible, and customizable reinforcement learning benchmark. PGTG requires an agent to navigate procedurally generated tracks while having to manage momentum and being exposed to various stochastic obstacles and the unpredictable behavior of traffic participants. By providing fine-grained control over the map generation, traffic rules, obstacles, and the observation and reward functions, PGTG is a versatile benchmark for various reinforcement learning subfields, such as exploration, safety, and generalization. For instance, PGTG allows decoupling safety from exploration by including subgoals with intermediate rewards. In this paper, we detail the benchmark’s modular design philosophy and provide a comprehensive empirical evaluation using state-of-the-art deep reinforcement learning baselines, highlighting PGTG’s complexity and utility for future research. Our code is available at github.