paper-with-me

Papers

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

2025-05-18 · Shuo Han, German Espinosa, Junda Huang, Daniel A. Dombeck, Malcolm A. MacIver, Bradly C. Stadie

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.

📄 PDF Abstract BibTeX arXiv:2505.12204

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Are deep learning models superior for missing data imputation in large surveys? Evidence from an empirical comparison

2021-03-14 · Zhenhua Wang, Olanrewaju Akande, Jason Poulos, Fan Li

Multiple imputation (MI) is a popular approach for dealing with missing data arising from non-response in sample surveys. Multiple imputation by chained equations (MICE) is one of the most widely used MI algorithms for m…

Deep LearningDenoisingImputation

MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools

2025-04-28 · Nishant Subramani, Jason Eisner, Justin Svegliato, Benjamin Van Durme 외

Tool-using agents that act in the world need to be both useful and safe. Well-calibrated model confidences can be used to weigh the risk versus reward of potential actions, but prior work shows that many models are poorl…

tBayes-MICE: A Bayesian Approach to Multiple Imputation for Time Series Data

2026-03-28 · Amuche Ibenegbu, Pierre Lafaye de Micheaux, Rohitash Chandra arxiv

Time-series analysis is often affected by missing data, a common problem across several fields, including healthcare and environmental monitoring. Multiple Imputation by Chained Equations (MICE) has been prominent for im…

Bayesian Inference

Energy Balance in Cell Phone Radiofrequency Radiation Exposed Mice and Rats

2019-04-29

The National Toxicology Program exposed mice and rats to cell phone radiofrequency radiation. They observer cancers in male rats but not in male mice and different increases in body temperature between mice and rats usin…

Learning Reward Machines from Partially Observed Policies

2025-02-06 · Mohamad Louai Shehab, Antoine Aspeel, Necmiye Ozay

Inverse reinforcement learning is the problem of inferring a reward function from an optimal policy or demonstrations by an expert. In this work, it is assumed that the reward is expressed as a reward machine whose trans…