gComm: An environment for investigating generalization in Grounded Language Acquisition
Not on the map. Why?
Abstract (arXiv)
gComm is a step towards developing a robust platform to foster research in grounded language acquisition in a more challenging and realistic setting. It comprises a 2-d grid environment with a set of agents (a stationary speaker and a mobile listener connected via a communication channel) exposed to a continuous array of tasks in a partially observable setting. The key to solving these tasks lies in agents developing linguistic abilities and utilizing them for efficiently exploring the environment. The speaker and listener have access to information provided in different modalities, i.e. the speaker's input is a natural language instruction that contains the target and task specifications and the listener's input is its grid-view. Each must rely on the other to complete the assigned task, however, the only way they can achieve the same, is to develop and use some form of communication. gComm provides several tools for studying different forms of communication and assessing their generalization.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 9 May 2021.
Builds on
20 of 28 references.
References · 20
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
- 2015VQA: Visual Question Answeringcited by 2,506
- 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 372
- 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 366
- 2017Embodied Question Answeringcited by 336
- 2015MovieQA: Understanding Stories in Movies through Question-Answeringcited by 304
- 2018Visual Reinforcement Learning with Imagined Goalscited by 251
- 2016Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Groundingcited by 243
- 2017Cognitive Mapping and Planning for Visual Navigationcited by 212
- 2019Planning with Goal-Conditioned Policiescited by 149
- 2017Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbolscited by 125
- 2020A Benchmark for Systematic Generalization in Grounded Language Understandingcited by 108
8 more
- 2019Cycle-Consistency for Robust Visual Question Answeringcited by 105
- 2017Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learningcited by 98
- 2017Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialogcited by 86
- 2019On the Pitfalls of Measuring Emergent Communicationcited by 71
- 2019Ease-of-Teaching and Language Structure from Emergent Communicationcited by 65
- 2018Emergent Communication through Negotiationcited by 62
- 2018Talk the Walk: Navigating New York City through Grounded Dialoguecited by 44
- 2019Embodied Language Grounding with 3D Visual Feature Representationscited by 20
Built on by
Citing papers per year: 2025: 1.
1 paper.