C-Procgen: Empowering Procgen with Controllable Contexts

TL;DR

C-Procgen extends the Procgen benchmark by providing over 200 configurable game contexts, enabling more transparent and adaptable environment generation for diverse reinforcement learning research.

Contribution

It introduces a controllable context framework for Procgen, enhancing environment customization and research applicability.

Findings

Over 200 unique game contexts available

Enhanced environment configurability and transparency

Supports diverse RL research areas

Abstract

We present C-Procgen, an enhanced suite of environments on top of the Procgen benchmark. C-Procgen provides access to over 200 unique game contexts across 16 games. It allows for detailed configuration of environments, ranging from game mechanics to agent attributes. This makes the procedural generation process, previously a black-box in Procgen, more transparent and adaptable for various research needs.The upgrade enhances dynamic context management and individualized assignments, while maintaining computational efficiency. C-Procgen's controllable contexts make it applicable in diverse reinforcement learning research areas, such as learning dynamics analysis, curriculum learning, and transfer learning. We believe that C-Procgen will fill a gap in the current literature and offer a valuable toolkit for future works.