mlsanityData to 7 Oct 2026

Empowerment -- an Introduction

arXiv 1310.1863 ↗First posted 7 Oct 2013cs.AI cs.IT math.ITcited by 65

Not on the map. Why?

Abstract (arXiv)

This book chapter is an introduction to and an overview of the information-theoretic, task independent utility function "Empowerment", which is defined as the channel capacity between an agent's actions and an agent's sensors. It quantifies how much influence and control an agent has over the world it can perceive. This book chapter discusses the general idea behind empowerment as an intrinsic motivation and showcases several previous applications of empowerment to demonstrate how empowerment can be applied to different sensor-motor configuration, and how the same formalism can lead to different observed behaviors. Furthermore, we also present a fast approximation for empowerment in the continuous domain.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Oct 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 0; 2020: 0; 2021: 16; 2022: 6; 2023: 6; 2024: 5; 2025: 15; 2026: 15.

65 papers.

Sort:

By area:

  1. 2018Reward learning from human preferences and demonstrations in Ataricited by 314
  2. 2021Causal Influence Detection for Improving Efficiency in Reinforcement Learningcited by 70
  3. 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
  4. 2021Towards Robust Bisimulation Metric Learningcited by 49
  5. 2021MADE: Exploration via Maximizing Deviation from Explored Regionscited by 40
  6. 2018Adversarial Imitation via Variational Inverse Reinforcement Learningcited by 36
  7. 2021The Information Geometry of Unsupervised Reinforcement Learningcited by 36
  8. 2024MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximizationcited by 30
  9. 2025Characterizing AI Agents for Alignment and Governancecited by 30
  10. 2022An information-theoretic perspective on intrinsic motivation in reinforcement learning: a surveycited by 25
  11. 2021Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learningcited by 21
  12. 2021Mutual Information State Intrinsic Controlcited by 18
38 more
  1. 2021Active Hierarchical Exploration with Stable Subgoal Representation Learningcited by 17
  2. 2021Understanding the World Through Actioncited by 17
  3. 2021Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learningcited by 15
  4. 2021Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learningcited by 15
  5. 2024Learning to Assist Humans without Inferring Rewardscited by 12
  6. 2021Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximizationcited by 11
  7. 2023CLUE: Calibrated Latent Guidance for Offline Reinforcement Learningcited by 11
  8. 2023Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skillscited by 8
  9. 2022Intrinsic Motivation in Dynamical Control Systemscited by 7
  10. 2023Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learningcited by 7
  11. 2025SOMBRL: Scalable and Optimistic Model-Based RLcited by 7
  12. 2021Explore and Control with Adversarial Surprisecited by 6
  13. 2023Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domainscited by 6
  14. 2023Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skillscited by 6
  15. 2025Intrinsically-Motivated Humans and Agents in Open-World Explorationcited by 6
  16. 2025From Curiosity to Competence: How World Models Interact with the Dynamics of Explorationcited by 5
  17. 2021Unsupervised Skill-Discovery and Skill-Learning in Minecraftcited by 4
  18. 2024BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shapingcited by 4
  19. 2025Towards Empowerment Gain through Causal Structure Learning in Model-Based RLcited by 4
  20. 2021Learning Task Agnostic Skills with Data-driven Guidancecited by 3
  21. 2022Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learningcited by 3
  22. 2025Sample-efficient and Scalable Exploration in Continuous-Time RLcited by 3
  23. 2022The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learningcited by 2
  24. 2022Empowered Neural Cellular Automatacited by 2
  25. 2025On Efficient Bayesian Exploration in Model-Based Reinforcement Learningcited by 2
  26. 2025Agent-centric learning: from external reward maximization to internal knowledge curationcited by 2
  27. 2025Estimating the Empowerment of Language Model Agentscited by 2
  28. 2025Training LLM Agents to Empower Humanscited by 2
  29. 2025Empowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventionscited by 2
  30. 2026Intelligence from Learnable Noveltycited by 2
  31. 2021Experimental Evidence that Empowerment May Drive Exploration in Sparse-Reward Environmentscited by 1
  32. 2023Selection for short-term empowerment accelerates the evolution of homeostatic neural cellular automatacited by 1
  33. 2024Latent-Predictive Empowerment: Measuring Empowerment without a Simulatorcited by 1
  34. 2024SuPLE: Robot Learning with Lyapunov Rewardscited by 1
  35. 2025Information-Theoretic Policy Pre-Training with Empowermentcited by 1
  36. 2026A Mathematical Theory of Agency and Intelligencecited by 1
  37. 2026Constructive Alignment: Governing Preference Dynamics in Human-AI Interactioncited by 1
  38. 2022Intrinsically motivated option learning: a comparative study of recent methodscited by 0

50 most cited of 65 All 65 (JSON)