mlsanityData to 7 Oct 2026

A survey on intrinsic motivation in reinforcement learning

arXiv 1908.06976 ↗First posted 19 Aug 2019cs.LG cs.AIcited by 79

Not on the map. Why?

Abstract (arXiv)

The reinforcement learning (RL) research area is very active, with an important number of new contributions; especially considering the emergent field of deep RL (DRL). However a number of scientific and technical challenges still need to be addressed, amongst which we can mention the ability to abstract actions or the difficulty to explore the environment which can be addressed by intrinsic motivation (IM). In this article, we provide a survey on the role of intrinsic motivation in DRL. We categorize the different kinds of intrinsic motivations and detail for each category, its advantages and limitations with respect to the mentioned challenges. Additionnally, we conduct an in-depth investigation of substantial current research questions, that are currently under study or not addressed at all in the considered research area of DRL. We choose to survey these research works, from the perspective of learning how to achieve tasks. We suggest then, that solving current challenges could lead to a larger developmental architecture which may tackle most of the tasks. We describe this developmental architecture on the basis of several building blocks composed of a RL algorithm and an IM module compressing information.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 19; 2023: 18; 2024: 16; 2025: 9; 2026: 4.

79 papers.

Sort:

By area:

  1. 2022The Alignment Problem from a Deep Learning Perspectivecited by 246
  2. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 185
  3. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 158
  4. 2021Reinforcement learning for optimization of variational quantum circuit architecturescited by 76
  5. 2023OMNI: Open-endedness via Models of human Notions of Interestingnesscited by 66
  6. 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
  7. 2021Towards Robust Bisimulation Metric Learningcited by 49
  8. 2023Augmenting Autotelic Agents with Large Language Modelscited by 29
  9. 2021Improving Playtesting Coverage via Curiosity Driven Reinforcement Learning Agentscited by 28
  10. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
  11. 2022EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RLcited by 23
  12. 2023Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Explorationcited by 20
38 more
  1. 2024A social path to human-like artificial intelligencecited by 20
  2. 2021Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learningcited by 15
  3. 2024The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Modelscited by 15
  4. 2024Learning to Assist Humans without Inferring Rewardscited by 12
  5. 2023Guarded Policy Optimization with Imperfect Online Demonstrationscited by 10
  6. 2023Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challengescited by 10
  7. 2021Deep KKL: Data-driven Output Prediction for Non-Linear Systemscited by 9
  8. 2022A Mixture of Surprises for Unsupervised Reinforcement Learningcited by 9
  9. 2022Foundation Models for Semantic Novelty in Reinforcement Learningcited by 9
  10. 2024Language Guided Exploration for RL Agents in Text Environmentscited by 9
  11. 2022An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environmentscited by 8
  12. 2021Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivationcited by 7
  13. 2021BR-NS: an Archive-less Approach to Novelty Searchcited by 7
  14. 2021DisTop: Discovering a Topological representation to learn diverse and rewarding skillscited by 7
  15. 2022Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and Investigationcited by 7
  16. 2022From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Taskscited by 6
  17. 2022CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectoriescited by 6
  18. 2023MIMEx: Intrinsic Rewards from Masked Input Modelingcited by 6
  19. 2025Intrinsically-Motivated Humans and Agents in Open-World Explorationcited by 6
  20. 2021Discovering and Exploiting Sparse Rewards in a Learned Behavior Spacecited by 5
  21. 2022Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Searchcited by 5
  22. 2023An Invitation to Deep Reinforcement Learningcited by 5
  23. 2022Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?cited by 4
  24. 2022CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learningcited by 4
  25. 2024Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Modelscited by 4
  26. 2024Visual Grounding for Object-Level Generalization in Reinforcement Learningcited by 4
  27. 2025LLM-Driven Intrinsic Motivation for Sparse Reward Reinforcement Learningcited by 4
  28. 2022Towards Artificial Virtuous Agents: Games, Dilemmas and Machine Learningcited by 3
  29. 2023Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Reviewcited by 3
  30. 2023Intrinsically motivated graph exploration using network theories of human curiositycited by 3
  31. 2024How to Choose a Reinforcement-Learning Algorithmcited by 3
  32. 2025Sample-efficient and Scalable Exploration in Continuous-Time RLcited by 3
  33. 2021Influence-Based Reinforcement Learning for Intrinsically-Motivated Agentscited by 2
  34. 2023Self-supervised network distillation: an effective approach to exploration in sparse reward environmentscited by 2
  35. 2024Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learningcited by 2
  36. 2025From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learningcited by 2
  37. 2025Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problemscited by 2
  38. 2025Learning Soft Robotic Dynamics with Active Explorationcited by 2

50 most cited of 79 All 79 (JSON)