mlsanityData to 14 Oct 2026

An Information-Theoretic Definition for Open-Ended Learning

arXiv 2606.08369 ↗First posted 6 Jun 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

A growing body of work points to the great promise of AI systems that can continually expand their capabilities as they operate in an open-ended environment. But yet there is no coherent definition of open-endedness or theory about how an agent ought to explore an open-ended environment. We introduce an information-theoretic definition based on a new concept -- the textit bit-equivalent -- which quantifies the information required to attain each level of expected reward. We consider an environment to be open-ended if an agent can attain linear growth in the bit-equivalent. We establish that classical bandit environments are not open-ended and formulate a bandit environment that is. We also introduce an algorithm that achieves open-ended learning in this environment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 49 references that are in the map. First posted on arXiv 6 Jun 2026.

Builds on

28 of 49 references.

References · 28

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  3. 2018Exploration by Random Network Distillationcited by 993
  4. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 356
  5. 2017On Kernelized Multi-armed Banditscited by 352
  6. 2013Learning to Optimize Via Posterior Samplingcited by 256
  7. 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 192
  8. 2026Towards End-to-End Automation of AI Researchcited by 159
  9. 2020On Information Gain and Regret Bounds in Gaussian Process Banditscited by 158
  10. 2020RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environmentscited by 135
  11. 2020Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutionscited by 106
  12. 2018Model-Based Active Explorationcited by 105
16 more
  1. 2023Motif: Intrinsic Motivation from Artificial Intelligence Feedbackcited by 102
  2. 2023A Definition of Continual Reinforcement Learningcited by 101
  3. 2020Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Surveycited by 85
  4. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 80
  5. 2025A Self-Improving Coding Agentcited by 79
  6. 2024OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Codecited by 74
  7. 2023OMNI: Open-endedness via Models of human Notions of Interestingnesscited by 70
  8. 2015Simple regret for infinitely many armed banditscited by 39
  9. 2018Satisficing in Time-Sensitive Bandit Learningcited by 39
  10. 2023MCU: An Evaluation Framework for Open-Ended Game Agentscited by 34
  11. 2021Deciding What to Learn: A Rate-Distortion Approachcited by 23
  12. 2025Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learningcited by 22
  13. 2023A Definition of Open-Ended Learning Problems for Goal-Conditioned Agentscited by 18
  14. 2024Boundless Socratic Learning with Language Gamescited by 12
  15. 2024On Creativity and Open-Endednesscited by 1
  16. 2026Prior Diffusiveness and Regret in the Linear-Gaussian Banditcited by 1

Built on by

Not cited yet.