# Programmable Agents

arXiv: https://arxiv.org/abs/1706.06383 · HTML: https://mlsanity.com/paper/1706.06383/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2017.

## Built on by (most cited first, 14 of 14)

- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation](https://mlsanity.com/paper/2109.01115/) (2021)
- [Learning to Understand Goal Specifications by Modelling Reward](https://mlsanity.com/paper/1806.01946/) (2018)
- [LTL2Action: Generalizing LTL Instructions for Multi-Task RL](https://mlsanity.com/paper/2102.06858/) (2021)
- [Robust Counterfactual Explanations on Graph Neural Networks](https://mlsanity.com/paper/2107.04086/) (2021)
- [TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs](https://mlsanity.com/paper/2207.05006/) (2022)
- [CompILE: Compositional Imitation Learning and Execution](https://mlsanity.com/paper/1812.01483/) (2018)
- [Discovering Generalizable Skills via Automated Generation of Diverse Tasks](https://mlsanity.com/paper/2106.13935/) (2021)
- [RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents](https://mlsanity.com/paper/2208.06448/) (2022)
- [Identifying Selections for Unsupervised Subtask Discovery](https://mlsanity.com/paper/2410.21616/) (2024)
- [SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization](https://mlsanity.com/paper/2202.13100/) (2022)
- [HypRL: Reinforcement Learning of Control Policies for Hyperproperties](https://mlsanity.com/paper/2504.04675/) (2025)
- [Boosting Exploration in Multi-Task Reinforcement Learning using Adversarial Networks](https://mlsanity.com/paper/2201.11783/) (2022)
- [Syntactic Inductive Biases for Deep Learning Methods](https://mlsanity.com/paper/2206.04806/) (2022)

## Abstract (arXiv)

We build deep RL agents that execute declarative programs expressed in formal language. The agents learn to ground the terms in this language in their environment, and can generalize their behavior at test time to execute new programs that refer to objects that were not referenced during training. The agents develop disentangled interpretable representations that allow them to generalize to a wide variety of zero-shot semantic tasks.