mlsanityData to 14 Oct 2026

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

arXiv 2505.12204 ↗First posted 18 May 2025cs.LG q-bio.NCcited by 2

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 21 of its 63 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

21 of 63 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  5. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  6. 2018World Modelscited by 1,513
  7. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  8. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  9. 2018Behavioral Cloning from Observationcited by 492
  10. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  11. 2021COMBO: Conservative Offline Model-Based Policy Optimizationcited by 370
  12. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 297
9 more
  1. 2015Incentivizing Exploration In Reinforcement Learning With Deep Predictive Modelscited by 154
  2. 2017Imagination-Augmented Agents for Deep Reinforcement Learningcited by 140
  3. 2017Third-Person Imitation Learningcited by 103
  4. 2020Deep Reinforcement Learning and its Neuroscientific Implicationscited by 33
  5. 2022DreamingV2: Reinforcement Learning with Discrete World Models without Reconstructioncited by 29
  6. 2023Mortal Computation: A Foundation for Biomimetic Intelligencecited by 15
  7. 2018A Biologically Plausible Learning Rule for Deep Learning in the Braincited by 9
  8. 2019SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environmentscited by 9
  9. 2020Reinforcement Learning and its Connections with Neuroscience and Psychologycited by 7

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025D2 Actor Critic: Diffusion Actor Meets Distributional Criticcited by 0
  2. 2025MoRE: Batch-Robust Multi-Omics Representations from Frozen Pre-trained Transformerscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026From Optimal Policies to Individual Differences: Rethinking Reinforcement Learning for Biology
  2. 2025Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
  3. 2025Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
  4. 2024Emergent Dominance Hierarchies in Reinforcement Learning Agents
  5. 2024Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics through Multi-Agent Reinforcement Learning Algorithms
  6. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
  7. 2024Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice
  8. 2025World Models Unlock Optimal Foraging Strategies in Reinforcement Learning Agents