Pith. sign in

REVIEW 3 cited by

Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1611.03218 v4 pith:3767GWKN submitted 2016-11-10 cs.AI cs.CLcs.LGcs.MA

classification cs.AIcs.CLcs.LGcs.MA
keywords agentslanguagecommunicationconceptsdialogueencodeenvironmentgame
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Acquiring your first language is an incredible feat and not easily duplicated. Learning to communicate using nothing but a few pictureless books, a corpus, would likely be impossible even for humans. Nevertheless, this is the dominating approach in most natural language processing today. As an alternative, we propose the use of situated interactions between agents as a driving force for communication, and the framework of Deep Recurrent Q-Networks for evolving a shared language grounded in the provided environment. We task the agents with interactive image search in the form of the game Guess Who?. The images from the game provide a non trivial environment for the agents to discuss and a natural grounding for the concepts they decide to encode in their communication. Our experiments show that the agents learn not only to encode physical concepts in their words, i.e. grounding, but also that the agents learn to hold a multi-step dialogue remembering the state of the dialogue from step to step.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketching

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    Scaling population size during training of emergent sketching agents increases zero-shot mutual intelligibility between independent groups by raising in-group variation and driving perceptual grounding.

  2. Mastering emergent language: learning to guide in simulated navigation

    cs.CL 2019-08 conditional novelty 6.0 of 10

    A Guide agent trained with a two-token discrete bottleneck learns an emergent guidance language that speeds up a new agent's navigation learning in BabyAI and can be partially reverse-engineered into action commands.

  3. A Review of Cooperative Multi-Agent Deep Reinforcement Learning

    cs.LG 2019-08 conditional novelty 1.0 of 10

    A review that categorizes cooperative multi-agent deep RL into independent learners, observable critics, value factorization, consensus, and communication, with errors in the taxonomy and references.

Pith tools