mlsanityData to 14 Oct 2026

Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning

arXiv 2306.11483 ↗First posted 20 Jun 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e. the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezuma's Revenge - one of the most challenging RL tasks in the Atari2600 game suite. We propose Int-HRL: Hierarchical RL with intention-based sub-goals that are inferred from human eye gaze. Our novel sub-goal extraction pipeline is fully automatic and replaces the need for manual sub-goal annotation by human experts. Our evaluations show that replacing hand-crafted sub-goals with automatically extracted intentions leads to a HRL agent that is significantly more sample efficient than previous methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 50 references that are in the map. First posted on arXiv 20 Jun 2023.

Builds on

27 of 50 references.

References · 27

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  4. 2015Prioritized Experience Replaycited by 1,099
  5. 2018Exploration by Random Network Distillationcited by 993
  6. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  7. 2017Deep Reinforcement Learning that Matterscited by 754
  8. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  9. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 337
  10. 2020Agent57: Outperforming the Atari Human Benchmarkcited by 303
  11. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 286
  12. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
15 more
  1. 2020Never Give Up: Learning Directed Exploration Strategiescited by 212
  2. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 207
  3. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 179
  4. 2019Unsupervised State Representation Learning in Ataricited by 144
  5. 2018Hierarchical Imitation and Reinforcement Learningcited by 88
  6. 2018Learning Montezuma's Revenge from a Single Demonstrationcited by 80
  7. 2023POPGym: Benchmarking Partially Observable Reinforcement Learningcited by 62
  8. 2015CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Researchcited by 52
  9. 2019Contextual Encoder-Decoder Network for Visual Saliency Predictioncited by 44
  10. 2018AGIL: Learning Attention from Human for Visuomotor Taskscited by 32
  11. 2021Discovery of Options via Meta-Learned Subgoalscited by 27
  12. 2020A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Reviewcited by 15
  13. 2021A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutionscited by 12
  14. 2023Gaze-based intention estimation: principles, methodologies, and applications in HRIcited by 11
  15. 2022The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learningcited by 2

Built on by

Not cited yet.