aiqbench analysis
The MAYA framework demonstrates that a multi-armed bandit approach effectively models individual bee foraging by incorporating a short-term memory window of approximately seven trials. By leveraging Wasserstein distance, the model outperforms classical baselines while offering interpretable insights into learning strategies and realistic trajectory inference. This work bridges sequential decision-making theory with ecological applications, validating the method across real, simulated, and cross-species datasets.
Buzz, Choose, Forget: A Meta-Bandit Framework for Bee-Like Decision Making
arXiv:2510.16462v3 Announce Type: replace Abstract: This work introduces MAYA, a sequential imitation learning model based on multi-armed bandits, designed to reproduce and predict individual bees' decisions in contextualized foraging tasks. The model accounts for bees' limited memory through a temporal window $\tau$, whose optimal value is around 7 trials, with a slight dependence on weather conditions. Experimental results on real, simulated, and complementary (mice) datasets show that MAYA (particularly with the Wasserstein distance) outperforms imitation baselines and classical statistical models, while providing interpretability of individual learning strategies and enabling the inference of realistic trajectories for prospective ecological applications.
Abstract:This work introduces MAYA, a sequential imitation learning model based on multi-armed bandits, designed to reproduce and predict individual bees' decisions in contextualized foraging tasks. The model accounts for bees' limited memory through a temporal window $\tau$, whose optimal value is around 7 trials, with a slight dependence on weather conditions. Experimental results on real, simulated, and complementary (mice) datasets show that MAYA (particularly with the Wasserstein distance) outperforms imitation baselines and classical statistical models, while providing interpretability of individual learning strategies and enabling the inference of realistic trajectories for prospective ecological applications.
Machine Learning (cs.LG); Machine Learning (stat.ML)
arXiv:2510.16462 [cs.LG]
(or arXiv:2510.16462v3 [cs.LG] for this version)
Full text under the publisher's open licence · 107 words