Leveraging Procedural Generation To Benchmark Reinforcement Learning

Abstract

We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learning. We believe that the community will benefit from increased access to high quality training environments, and we provide detailed experimental protocols for using this benchmark. We empirically demonstrate that diverse environment distributions are essential to adequately train and evaluate RL agents, thereby motivating the extensive use of procedural content generation. We then use this benchmark to investigate the effects of scaling model size, finding that larger models significantly improve both sample efficiency and generalization.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycobbe2019leveraging

Related papers

• Measuring Sample Efficiency And Generalization In Reinforcement Learning Benchmarks: Neurips 2020 Procgen Benchmark (2021)0.00
• Illuminating Generalization In Deep Reinforcement Learning Through Procedural Level Generation (2018)0.00
• C-procgen: Empowering Procgen With Controllable Contexts (2023)0.00
• Improving Generalization On The Procgen Benchmark With Simple Architectural Changes And Scale (2024)0.00
• Procedural Generalization By Planning With Self-supervised World Models (2021)0.00
• Quantifying Generalization In Reinforcement Learning (2018)0.00
• Assessing Generalization In Deep Reinforcement Learning (2018)0.00
• Procedural Generation Of Meta-reinforcement Learning Tasks (2023)0.00