mlsanityData to 7 Oct 2026

From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Tasks

arXiv 2201.08300 ↗First posted 20 Jan 2022cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Psychological curiosity plays a significant role in human intelligence to enhance learning through exploration and information acquisition. In the Artificial Intelligence (AI) community, artificial curiosity provides a natural intrinsic motivation for efficient learning as inspired by human cognitive development; meanwhile, it can bridge the existing gap between AI research and practical application scenarios, such as overfitting, poor generalization, limited training samples, high computational cost, etc. As a result, curiosity-driven learning (CDL) has become increasingly popular, where agents are self-motivated to learn novel knowledge. In this paper, we first present a comprehensive review on the psychological study of curiosity and summarize a unified framework for quantifying curiosity as well as its arousal mechanism. Based on the psychological principle, we further survey the literature of existing CDL methods in the fields of Reinforcement Learning, Recommendation, and Classification, where both advantages and disadvantages as well as future work are discussed. As a result, this work provides fruitful insights for future CDL research and yield possible directions for further improvement.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 48 of its 155 references that are in the map. First posted on arXiv 20 Jan 2022.

Builds on

48 of 155 references.

References · 48

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  3. 2015Variational Inference with Normalizing Flowscited by 2,161
  4. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  5. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  6. 2015Prioritized Experience Replaycited by 1,070
  7. 2018Exploration by Random Network Distillationcited by 966
  8. 2018DeepMind Control Suitecited by 935
  9. 2016Deep Variational Information Bottleneckcited by 915
  10. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
  11. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  12. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
36 more
  1. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
  2. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  3. 2020Reinforcement Learning with Augmented Datacited by 452
  4. 2020Planning to Explore via Self-Supervised World Modelscited by 365
  5. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 361
  6. 2016#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learningcited by 307
  7. 2018Large-Scale Study of Curiosity-Driven Learningcited by 277
  8. 2019Improving Sample Efficiency in Model-Free Reinforcement Learning from Imagescited by 268
  9. 2019Self-Supervised Exploration via Disagreementcited by 263
  10. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 259
  11. 2017Count-Based Exploration with Neural Density Modelscited by 255
  12. 2020Prioritized Level Replaycited by 190
  13. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 165
  14. 2015Incentivizing Exploration In Reinforcement Learning With Deep Predictive Modelscited by 154
  15. 2020RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environmentscited by 135
  16. 2018Episodic Curiosity through Reachabilitycited by 109
  17. 2014Collaborative Deep Learning for Recommender Systemscited by 95
  18. 2020Learning with AMIGo: Adversarially Motivated Intrinsic Goalscited by 86
  19. 2017The Uncertainty Bellman Equation and Explorationcited by 81
  20. 2019A survey on intrinsic motivation in reinforcement learningcited by 79
  21. 2019InfoBot: Transfer and Exploration via the Information Bottleneckcited by 78
  22. 2017EX2: Exploration with Exemplar Models for Deep Reinforcement Learningcited by 42
  23. 2018Uncertainty in the Variational Information Bottleneckcited by 39
  24. 2020Intrinsic Reward Driven Imitation Learning via Generative Modelcited by 35
  25. 2017Trust-PCL: An Off-Policy Trust Region Method for Continuous Controlcited by 29
  26. 2019Curiosity-Driven Experience Prioritization via Density Estimationcited by 27
  27. 2021MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learningcited by 24
  28. 2019Prioritized Sequence Experience Replaycited by 20
  29. 2021Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Modelcited by 14
  30. 2020Reinforcement Learning Generalization with Surprise Minimizationcited by 10
  31. 2018Attention-based Active Visual Search for Mobile Robotscited by 7
  32. 2019Bayesian Curiosity for Efficient Exploration in Reinforcement Learningcited by 7
  33. 2021Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearitycited by 6
  34. 2021Explore and Control with Adversarial Surprisecited by 6
  35. 2019One Size Does Not Fit All: Modeling Users' Personal Curiosity in Recommender Systemscited by 2
  36. 2019Curiosity-Driven Recommendation Strategy for Adaptive Learning via Deep Reinforcement Learningcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1; 2025: 2.

6 papers.

  1. 2022A Mixture of Surprises for Unsupervised Reinforcement Learningcited by 9
  2. 2022CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learningcited by 4
  3. 2023CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learningcited by 0
  4. 2024Automating Creativitycited by 0
  5. 2025A Computational Model of Inclusive Pedagogy: From Understanding to Applicationcited by 0
  6. 2025A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agentscited by 0