20220108-MTOA: Accuracy improvement from undertaking additional overlapping tasks follows a law of diminishing returns.

This archive contains the results of a multi-agent simulation experiment [1] carried out with Lazy lavender [2] environment.

Experiment Label: MTOA-20220108

Experiment design: Agents improve average accuracy by tackling several tasks.

Experiment setting: Agents are trained with respect to different tasks and then coordinate upon acting on them. Each time they disagree, one agent adapts its knowledge with respect to the current task.

Hypotheses: The higher is the number of carried out tasks, the higher the average accuracy is.

Detailed information can be found in index.html or notebook.ipynb.

[1] https://sake.re/20220108-MTOA
[2] https://gitlab.inria.fr/moex/lazylav/