# Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent

arXiv: https://arxiv.org/abs/1711.07950 · HTML: https://mlsanity.com/paper/1711.07950/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2017.

## Built on by (most cited first, 10 of 10)

- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [CommonsenseQA 2.0: Exposing the Limits of AI through Gamification](https://mlsanity.com/paper/2201.05320/) (2022)
- [Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models](https://mlsanity.com/paper/2106.00245/) (2021)
- [COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences](https://mlsanity.com/paper/2106.00969/) (2021)
- [On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study](https://mlsanity.com/paper/2106.00872/) (2021)
- [Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants](https://mlsanity.com/paper/2112.09062/) (2021)
- [Analyzing Dynamic Adversarial Training Data in the Limit](https://mlsanity.com/paper/2110.08514/) (2021)
- [ScatterShot: Interactive In-context Example Curation for Text Transformation](https://mlsanity.com/paper/2302.07346/) (2023)
- [Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset](https://mlsanity.com/paper/2403.19559/) (2024)
- [Targeted Data Acquisition for Evolving Negotiation Agents](https://mlsanity.com/paper/2106.07728/) (2021)

## Abstract (arXiv)

Contrary to most natural language processing research, which makes use of static datasets, humans learn language interactively, grounded in an environment. In this work we propose an interactive learning procedure called Mechanical Turker Descent (MTD) and use it to train agents to execute natural language commands grounded in a fantasy text adventure game. In MTD, Turkers compete to train better agents in the short term, and collaborate by sharing their agents' skills in the long term. This results in a gamified, engaging experience for the Turkers and a better quality teaching signal for the agents compared to static datasets, as the Turkers naturally adapt the training data to the agent's abilities.