Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents

TL;DR

This paper compares biological mice and reinforcement learning agents in a predator-avoidance task, revealing key behavioral differences and proposing mechanisms to make RL agents exhibit more naturalistic risk-avoidance behaviors.

Contribution

It introduces two novel mechanisms that enhance RL agents' risk assessment and avoidance behaviors, aligning them more closely with biological counterparts.

Findings

RL agents lack self-preservation instincts compared to mice.

Proposed mechanisms induce naturalistic risk-avoidance behaviors in RL agents.

RL agents exhibit strategic environment assessment and cautious planning.

Abstract

Recent advances in reinforcement learning (RL) have demonstrated impressive capabilities in complex decision-making tasks. This progress raises a natural question: how do these artificial systems compare to biological agents, which have been shaped by millions of years of evolution? To help answer this question, we undertake a comparative study of biological mice and RL agents in a predator-avoidance maze environment. Through this analysis, we identify a striking disparity: RL agents consistently demonstrate a lack of self-preservation instinct, readily risking ``death'' for marginal efficiency gains. These risk-taking strategies are in contrast to biological agents, which exhibit sophisticated risk-assessment and avoidance behaviors. Towards bridging this gap between the biological and artificial, we propose two novel mechanisms that encourage more naturalistic risk-avoidance behaviors in RL agents. Our approach leads to the emergence of naturalistic behaviors, including strategic environment assessment, cautious path planning, and predator avoidance patterns that closely mirror those observed in biological systems.