# Zero-Shot Action Generalization with Limited Observations

arXiv: https://arxiv.org/abs/2503.08867 · HTML: https://mlsanity.com/paper/2503.08867/

## 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.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Reinforcement Learning in Healthcare: A Survey](https://mlsanity.com/paper/1908.08796/) (2019)
- [Prioritized Level Replay](https://mlsanity.com/paper/2010.03934/) (2020)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Towards a Neural Statistician](https://mlsanity.com/paper/1606.02185/) (2016)
- [Observational Overfitting in Reinforcement Learning](https://mlsanity.com/paper/1912.02975/) (2019)
- [Decoupling Value and Policy for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2102.10330/) (2021)
- [Generalization to New Actions in Reinforcement Learning](https://mlsanity.com/paper/2011.01928/) (2020)
- [In-Context Reinforcement Learning for Variable Action Spaces](https://mlsanity.com/paper/2312.13327/) (2023)
- [Lifelong Learning with a Changing Action Set](https://mlsanity.com/paper/1906.01770/) (2019)
- [Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions](https://mlsanity.com/paper/2111.14629/) (2021)
- [Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation](https://mlsanity.com/paper/2106.15587/) (2021)
- [Rethinking Value Function Learning for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2210.09960/) (2022)
- [Action Pick-up in Dynamic Action Space Reinforcement Learning](https://mlsanity.com/paper/2304.00873/) (2023)

## 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.