Deep Reinforcement Learning Agents are not even close to Human Intelligence

Understand

Deep reinforcement learning (RL) agents achieve impressive results in a wide variety of tasks, but they lack zero-shot adaptation capabilities.

• While most robustness evaluations focus on tasks complexifications, for which human also struggle to maintain performances, no evaluation has been performed on tasks simplifications.
• To tackle this issue, we introduce HackAtari, a set of task variations of the Arcade Learning Environments.
• We use it to demonstrate that, contrary to humans, RL agents systematically exhibit huge performance drops on simpler versions of their training tasks, uncovering agents' consistent reliance on shortcuts.