mlsanityData to 14 Oct 2026

Zero-Shot Action Generalization with Limited Observations

arXiv 2503.08867 ↗First posted 11 Mar 2025cs.LG cs.AI cs.CVcited by 0

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

Abstract (arXiv)

Reinforcement Learning (RL) has demonstrated remarkable success in solving sequential decision-making problems. However, in real-world scenarios, RL agents often struggle to generalize when faced with unseen actions that were not encountered during training. Some previous works on zero-shot action generalization rely on large datasets of action observations to capture the behaviors of new actions, making them impractical for real-world applications. In this paper, we introduce a novel zero-shot framework, Action Generalization from Limited Observations (AGLO). Our framework has two main components: an action representation learning module and a policy learning module. The action representation learning module extracts discriminative embeddings of actions from limited observations, while the policy learning module leverages the learned action representations, along with augmented synthetic action representations, to learn a policy capable of handling tasks with unseen actions. The experimental results demonstrate that our framework significantly outperforms state-of-the-art methods for zero-shot action generalization across multiple benchmark tasks, showcasing its effectiveness in generalizing to new actions with minimal action observations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 18 of its 25 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

18 of 25 references.

References · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2017Robust Adversarial Reinforcement Learningcited by 451
  5. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  6. 2019Reinforcement Learning in Healthcare: A Surveycited by 310
  7. 2020Prioritized Level Replaycited by 198
  8. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  9. 2016Towards a Neural Statisticiancited by 121
  10. 2019Observational Overfitting in Reinforcement Learningcited by 91
  11. 2021Decoupling Value and Policy for Generalization in Reinforcement Learningcited by 82
  12. 2020Generalization to New Actions in Reinforcement Learningcited by 25
6 more
  1. 2023In-Context Reinforcement Learning for Variable Action Spacescited by 24
  2. 2019Lifelong Learning with a Changing Action Setcited by 17
  3. 2021Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functionscited by 17
  4. 2021Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentationcited by 15
  5. 2022Rethinking Value Function Learning for Generalization in Reinforcement Learningcited by 8
  6. 2023Action Pick-up in Dynamic Action Space Reinforcement Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Unified Framework for Zero-Shot Reinforcement Learning
  2. 2024Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning
  3. 2025Good Actions Succeed, Bad Actions Generalize: A Case Study on Why RL Generalizes Better
  4. 2026Improving Zero-Shot Offline RL via Behavioral Task Sampling
  5. 2025Towards Robust Zero-Shot Reinforcement Learning
  6. 2024A Minimalist Prompt for Zero-Shot Policy Learning
  7. 2024Foundation Policies with Hilbert Representations
  8. 2024Zero-Shot Reinforcement Learning via Function Encoders