Translating Neuralese
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Several approaches have recently been proposed for learning decentralized deep multiagent policies that coordinate via a differentiable communication channel.While these policies are effective for many tasks, interpretation of their induced communication strategies has remained a challenge.Here we propose to interpret agents' messages by translating them.Unlike in typical machine translation problems, we have no parallel data to learn from.Instead we develop a translation model based on the insight that agent messages and natural language strings mean the same thing if they induce the same belief about the world in a listener.We present theoretical guarantees and empirical evidence that our approach preserves both the semantics and pragmatics of messages by ensuring that players communicating through a translation layer do not suffer a substantial loss in reward relative to players with a common language.1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
Learning to Communicate with Deep Multi-Agent Reinforcement Learning
Foerster, J. N., Assael, Y. M., de Freitas, N., & Whiteson, S. (2016) · arXiv · doi:10.48550/arxiv.1605.06676 · Cited by 1,217 · cited 5×
“DCPs have been shown to solve a variety of coordination problems, including reference games (Lazaridou et al., 2016b), logic puzzles (Foerster et al., 2016), and simple control (Sukhbaatar et al., 2016).”
BackgroundMethodInfluentialThe Complexity of Decentralized Control of Markov Decision Processes
Bernstein, D. S., Givan, R., Immerman, N., & Zilberstein, S. (2002) · Mathematics of Operations Research · doi:10.1287/moor.27.4.819.297 · Cited by 1,192
Generating Visual Explanations
Hendricks, L. A., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., & Darrell, T. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_1 · Cited by 534
Multi-Agent Cooperation and the Emergence of (Natural) Language
Lazaridou, A., Peysakhovich, A., & Baroni, M. (2016) · arXiv · doi:10.48550/arxiv.1612.07182 · Cited by 231
Reasoning about Pragmatics with Neural Listeners and Speakers
Andreas, J., & Klein, D. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1125 · Cited by 115 · cited 1×
“Communication strategies for reference games were previously explored by Vogel et al. (2013a), Andreas and Klein (2016) and Kazemzadeh et al. (2014), and reference games specifically featuring end-to-end communication protocols by Yu et al. (2016).”
BackgroundSelf-citation
Cited by
Emergence of grounded compositional language in multi-agent populations
Mordatch, I., & Abbeel, P. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11492 · Cited by 440
Human‐centered artificial intelligence and machine learning
Riedl, M. O. (2019) · Human Behavior and Emerging Technologies · doi:10.1002/hbe2.117 · Cited by 371
Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
Das, A., Kottur, S., Moura, J. M. F., Lee, S., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.321 · Cited by 356
Automated rationale generation: a technique for explainable AI and its effects on human perceptions
Ehsan, U., Tambwekar, P., Chan, L., Harrison, B., & Riedl, M. O. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302316 · Cited by 210
Scalable agent alignment via reward modeling: a research direction
Leike, J., Krueger, D., Everitt, T., Martic, M., Maini, V., & Legg, S. (2018) · arXiv · doi:10.48550/arxiv.1811.07871 · Cited by 121
“, 2018), translating neural activations into natural language on tasks also performed by humans (Andreas et al., 2017), and combining different interactive visualization techniques (Olah et al.”
Background
Metadata
- Authors
- Andreas, J., Dragan, A., & Klein, D.
- Venue
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2017
- Pages
- 232-242
- OpenAlex
- W3089050900
- Cited by
- 39
- References
- 7
- FWCI
- 3.30
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Translating Neuralese. https://app.cochat.ai/papers/10.18653/v1/p17-1022
- The paper
- Andreas, J., Dragan, A., & Klein, D. (2017). Translating Neuralese. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/p17-1022
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.