Diagnosing And Exploiting The Computational Demands Of Videos Games For Deep Reinforcement Learning

Abstract

Humans learn by interacting with their environments and perceiving the outcomes of their actions. A landmark in artificial intelligence has been the development of deep reinforcement learning (dRL) algorithms capable of doing the same in video games, on par with or better than humans. However, it remains unclear whether the successes of dRL models reflect advances in visual representation learning, the effectiveness of reinforcement learning algorithms at discovering better policies, or both. To address this question, we introduce the Learning Challenge Diagnosticator (LCD), a tool that separately measures the perceptual and reinforcement learning demands of a task. We use LCD to discover a novel taxonomy of challenges in the Procgen benchmark, and demonstrate that these predictions are both highly reliable and can instruct algorithmic development. More broadly, the LCD reveals multiple failure cases that can occur when optimizing dRL algorithms over entire video game benchmarks like P

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygovindarajan2023diagnosing

Related papers

• A Survey Of Deep Reinforcement Learning In Video Games (2019)0.00
• Learning To Identify Critical States For Reinforcement Learning From Videos (2023)8.76
• Reinforcement Learning And Video Games (2019)0.00
• Odysseus: Scaling Vlms To 100+ Turn Decision-making In Games Via Reinforcement Learning (2026)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• Machine Versus Human Attention In Deep Reinforcement Learning Tasks (2020)0.00
• An Approach To Partial Observability In Games: Learning To Both Act And Observe (2021)3.58
• Importance Of Using Appropriate Baselines For Evaluation Of Data-efficiency In Deep Reinforcement Learning For Atari (2020)0.00