Minimal DRL-trained RNN agents reproduce larval zebrafish hunting motifs — vergence-linked pursuit and ~50% per-bout prey-angle reduction — without imitation learning, from binocular sensing, coupled bout kinematics, and small energetic costs alone.
PMID: 39719697
1 Pith paper cite this work, alongside 6 external citations. Polarity classification is still indexing.
1
Pith paper citing it
6
external citations · OpenAlex
fields
q-bio.NC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dissecting Larval Zebrafish Hunting using Deep Reinforcement Learning Trained RNN Agents
Minimal DRL-trained RNN agents reproduce larval zebrafish hunting motifs — vergence-linked pursuit and ~50% per-bout prey-angle reduction — without imitation learning, from binocular sensing, coupled bout kinematics, and small energetic costs alone.