We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| MathieuRita/Lazimpa | canonical | 4 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| dump_sender_receiver | Ran | MathieuRita/Lazimpa/egg/core/util.py code served (permissive licence) · get_code("91d0aad2cab137d2") |
| init | Ran | MathieuRita/Lazimpa/egg/core/util.py code served (permissive licence) · get_code("3c2081da5221dfd6") |
| parse_json_sweep | Ran | MathieuRita/Lazimpa/egg/nest/common.py code served (permissive licence) · get_code("4e69343bf76117a3") |
| sweep | Ran | MathieuRita/Lazimpa/egg/nest/common.py code served (permissive licence) · get_code("7febd697258e8673") |
| build_optimizer | Not yet run | MathieuRita/Lazimpa/egg/core/util.py code served (permissive licence) · get_code("e2719e4662b94c84") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Previous work has shown that artificial neural agents naturally develop surprisingly non-efficient codes. This is illustrated by the fact that in a referential game involving a speaker and a listener neural networks optimizing accurate transmission over a discrete channel, the emergent messages fail to achieve an optimal length. Furthermore, frequent messages tend to be longer than infrequent ones, a pattern contrary to the Zipf Law of Abbreviation (ZLA) observed in all natural languages. Here, we show that near-optimal and ZLA-compatible messages can emerge, but only if both the speaker and the listener are modified. We hence introduce a new communication system, "LazImpa", where the speaker is made increasingly lazy, i.e. avoids long messages, and the listener impatient, i.e.,~seeks to guess the intended content as soon as possible.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.01878")
get_code_for_paper("2010.01878")
have("2010.01878")
Connect an agent — have() is free.