Programmable Agents
Not on the map. Why?
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.
Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Jun 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2018: 2; 2019: 0; 2020: 0; 2021: 5; 2022: 5; 2023: 0; 2024: 1; 2025: 1.
14 papers.
Sort:
By area:
- 2021How Attentive are Graph Attention Networks?cited by 835
- 2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationcited by 118
- 2018Learning to Understand Goal Specifications by Modelling Rewardcited by 80
- 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 74
- 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
- 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphscited by 59
- 2018CompILE: Compositional Imitation Learning and Executioncited by 7
- 2021Discovering Generalizable Skills via Automated Generation of Diverse Taskscited by 5
- 2022RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agentscited by 4
- 2024Identifying Selections for Unsupervised Subtask Discoverycited by 4
- 2022SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalizationcited by 2
- 2025HypRL: Reinforcement Learning of Control Policies for Hyperpropertiescited by 2
2 more
- 2025HypRL: Reinforcement Learning of Control Policies for Hyperproperties7 Apr 2025
- 2024Identifying Selections for Unsupervised Subtask Discovery28 Oct 2024
- 2022RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents12 Aug 2022
- 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs11 Jul 2022
- 2022Syntactic Inductive Biases for Deep Learning Methods8 Jun 2022
- 2022SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization26 Feb 2022
- 2022Boosting Exploration in Multi-Task Reinforcement Learning using Adversarial Networks27 Jan 2022
- 2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation2 Sep 2021
- 2021Robust Counterfactual Explanations on Graph Neural Networks8 Jul 2021
- 2021Discovering Generalizable Skills via Automated Generation of Diverse Tasks26 Jun 2021
- 2021How Attentive are Graph Attention Networks?30 May 2021
- 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RL13 Feb 2021
2 more
- 2018CompILE: Compositional Imitation Learning and Executioncited by 7
- 2024Identifying Selections for Unsupervised Subtask Discoverycited by 4
- 2024Identifying Selections for Unsupervised Subtask Discovery28 Oct 2024
- 2018CompILE: Compositional Imitation Learning and Execution4 Dec 2018
- 2021How Attentive are Graph Attention Networks?cited by 835
- 2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationcited by 118
- 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 74
- 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
- 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphscited by 59
- 2021Discovering Generalizable Skills via Automated Generation of Diverse Taskscited by 5
- 2022RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agentscited by 4
- 2022SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalizationcited by 2
- 2022Boosting Exploration in Multi-Task Reinforcement Learning using Adversarial Networkscited by 0
- 2022Syntactic Inductive Biases for Deep Learning Methodscited by 0
- 2022RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents12 Aug 2022
- 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs11 Jul 2022
- 2022Syntactic Inductive Biases for Deep Learning Methods8 Jun 2022
- 2022SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization26 Feb 2022
- 2022Boosting Exploration in Multi-Task Reinforcement Learning using Adversarial Networks27 Jan 2022
- 2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation2 Sep 2021
- 2021Robust Counterfactual Explanations on Graph Neural Networks8 Jul 2021
- 2021Discovering Generalizable Skills via Automated Generation of Diverse Tasks26 Jun 2021
- 2021How Attentive are Graph Attention Networks?30 May 2021
- 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RL13 Feb 2021