# Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization

arXiv: https://arxiv.org/abs/2205.12648 · HTML: https://mlsanity.com/paper/2205.12648/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 25 May 2022.

## Builds on (most cited first, 23 of 23)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration](https://mlsanity.com/paper/1802.08802/) (2018)
- [Probabilistic Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.02817/) (2018)
- [Modular Multitask Reinforcement Learning with Policy Sketches](https://mlsanity.com/paper/1611.01796/) (2016)
- [Bayesian Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.03836/) (2018)
- [Acme: A Research Framework for Distributed Reinforcement Learning](https://mlsanity.com/paper/2006.00979/) (2020)
- [Meta-Reinforcement Learning of Structured Exploration Strategies](https://mlsanity.com/paper/1802.07245/) (2018)
- [Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning](https://mlsanity.com/paper/1706.05064/) (2017)
- [Neural Task Programming: Learning to Generalize Across Hierarchical Tasks](https://mlsanity.com/paper/1710.01813/) (2017)
- [Gated-Attention Architectures for Task-Oriented Language Grounding](https://mlsanity.com/paper/1706.07230/) (2017)
- [Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration](https://mlsanity.com/paper/1807.03480/) (2018)
- [Learning to Navigate the Web](https://mlsanity.com/paper/1812.09195/) (2018)
- [Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies](https://mlsanity.com/paper/1807.07665/) (2018)
- [Learning to Push by Grasping: Using multiple tasks for effective learning](https://mlsanity.com/paper/1609.09025/) (2016)
- [DOM-Q-NET: Grounded RL on Structured Language](https://mlsanity.com/paper/1902.07257/) (2019)
- [Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies](https://mlsanity.com/paper/2001.00248/) (2020)
- [A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment](https://mlsanity.com/paper/1703.09831/) (2017)
- [Autonomous Extracting a Hierarchical Structure of Tasks in Reinforcement Learning and Multi-task Reinforcement Learning](https://mlsanity.com/paper/1709.04579/) (2017)

## Built on by (most cited first, 3 of 3)

- [Multimodal Subtask Graph Generation from Instructional Videos](https://mlsanity.com/paper/2302.08672/) (2023)
- [Composing Task Knowledge with Modular Successor Feature Approximators](https://mlsanity.com/paper/2301.12305/) (2023)
- [TOD-Flow: Modeling the Structure of Task-Oriented Dialogues](https://mlsanity.com/paper/2312.04668/) (2023)

## Abstract (arXiv)

We tackle real-world problems with complex structures beyond the pixel-based game or simulator. We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph that defines a set of subtasks and their dependencies that are unknown to the agent. Different from the previous meta-rl methods trying to directly infer the unstructured task embedding, our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks, and use it as a prior to improve the task inference in testing. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks than various existing algorithms such as meta reinforcement learning, hierarchical reinforcement learning, and other heuristic agents.