# Evolutionary Algorithms Can Become Trapped in Mediocre Stable States by Jordan Pollack > “I work on the question of evolution, not as it exists in Nature, but as a formal system which enables open-ended learning. Can we understand the process in enough detail to simulate the progress of biological complexity in pure software or electronics? A phenomena has appeared in many of my laboratory's experiments in learning across many different domains like game playing and robots. We have dubbed it a "Mediocre Stable State." It is an unexpected systematic equilibrium, where a collection of sub-optimal agents act together to prevent further progress. In dynamical systems, the MSS hides within cycles of forgetting that which has been already been learned.” > **— Jordan Pollack**, *2002, Edge Annual Question, “What Is Your Question? ... Why?”* ## Sources and Context - **Direct Edge response and surrounding essay:** [Is there Progress?](https://www.edge.org/response-detail/11134) — Edge published this exact passage in its 2002 Annual Question collection, *WHAT IS YOUR QUESTION? ... WHY?*. The response page preserves the surrounding argument and qualifications. - **Complete local collection index:** [[research/Edge 2002 Full Quotation Curation|Edge 2002 Full Quotation Curation]] — retained source-first record for the complete response cohort and this passage's promotion status. ## Related Articles and Collections - **Collection:** [[collections/Edge|Edge]] - **Collection:** [[collections/Machine Succession|Machine Succession]] - **Article:** [[articles/The Evolutionary Roots of Silicon Valley|Valley Roots]] - **Article:** [[articles/Digital Darwinism and the Invisible World of Machine Evolution|Digital Darwinism]] - **Article:** [[articles/We Were Never Going to Make It|Never Going to Make It!]] - **Wiki map:** [[wiki/Evolutionary Biology|Evolutionary Biology]] ## Related Topics - [[wiki/Evolutionary Biology|Evolutionary Biology]] - [[wiki/human-machine interaction|human-machine interaction]] - [[wiki/Human-Machine Symbiosis|Human-Machine Symbiosis]] - [[wiki/Technological Evolution|Technological Evolution]] ## Share on Social Media ``` “I work on the question of evolution, not as it exists in Nature, but as a formal system which enables open-ended learning. Can we understand the process in enough detail to simulate the progress of biological complexity in pure software or electronics? A phenomena has appeared in many of my laboratory's experiments in learning across many different domains like game playing and robots. We have dubbed it a "Mediocre Stable State." It is an unexpected systematic equilibrium, where a collection of sub-optimal agents act together to prevent further progress. In dynamical systems, the MSS hides within cycles of forgetting that which has been already been learned.” — Jordan Pollack, 2002, Edge Annual Question, “What Is Your Question? ... Why?” https://bryantmcgill.com/simple-reminders-jordan-pollack-evolutionary-algorithms-become-trapped-mediocre ```