Deep Reinforcement Learning Agents are not even close to Human Intelligence

Quentin Delfosse, Jannis Blüml, Fabian Tatai, Théo Vincent, Bjarne Gregori, Elisabeth Dillies, Jan Peters, Constantin A. Rothkopf, Kristian Kersting

Keywords: Generalization, Shortcut Learning, Misalignment

TL;DR: We show that many deep and symbolic RL algorithm consistently produce agents that learn shortcuts, and thus cannot generalize to tasks simplifications.

Abstract:

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.
Our analysis across multiple algorithms and architectures highlights the persistent gap between RL agents and human behavioral intelligence, underscoring the need for new benchmarks and methodologies that enforce systematic generalization testing beyond static evaluation protocols.
Training and testing in the same environment is not enough to obtain agents equipped with human-like intelligence.

Confirmation: I understand that authors of each paper submitted to EWRL may be asked to review 2-3 other submissions to EWRL.

Serve As Reviewer: ~Jannis_Blüml1

Track: Regular Track: unpublished work

Submission Number: 64