mlsanityData to 14 Oct 2026

General Dynamic Goal Recognition using Goal-Conditioned and Meta Reinforcement Learning

arXiv 2505.09737 ↗First posted 14 May 2025cs.AI cs.ROcited by 1

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Understanding an agent's goal through its behavior is a common AI problem called Goal Recognition (GR). This task becomes particularly challenging in dynamic environments where goals are numerous and ever-changing. We introduce the General Dynamic Goal Recognition (GDGR) problem, a broader definition of GR aimed at real-time adaptation of GR systems. This paper presents two novel approaches to tackle GDGR: (1) GC-AURA, generalizing to new goals using Model-Free Goal-Conditioned Reinforcement Learning, and (2) Meta-AURA, adapting to novel environments with Meta-Reinforcement Learning. We evaluate these methods across diverse environments, demonstrating their ability to achieve rapid adaptation and high GR accuracy under dynamic and noisy conditions. This work is a significant step forward in enabling GR in dynamic and unpredictable real-world environments.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 33 references that are in the map. First posted on arXiv 14 May 2025.

Builds on

13 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Goal Recognition using Actor-Critic Optimization31 Dec
  2. 2024ODGR: Online Dynamic Goal Recognition23 Jul

Other references · 11

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2015Trust Region Policy Optimizationcited by 2,580
  3. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  4. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
  5. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 158
  6. 2020learn2learn: A Library for Meta-Learning Researchcited by 69
  7. 2021panda-gym: Open-source goal-conditioned environments for robotic learningcited by 59
  8. 2019Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interactioncited by 11
  9. 2017Intent Recognition in Smart Living Through Deep Recurrent Neural Networkscited by 9
  10. 2022Goal Recognition as a Deep Learning Task: the GRNet Approachcited by 9
  11. 2023Real-time goal recognition using approximations in Euclidean spacecited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Artificial Intelligent Disobedience: Rethinking the Agency of Our Artificial Teammatescited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2025Dual Goal Representations
  2. 2026GRAIL: Goal Recognition Alignment through Imitation Learning
  3. 2025Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning
  4. 2025Online Dynamic Goal Recognition in Gym Environments
  5. 2024Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks
  6. 2024MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning
  7. 2024Hierarchical Meta-Reinforcement Learning via Automated Macro-Action Discovery
  8. 2026Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization