Animal Behavior & CognitionComputational Brain & BehaviorPeer-reviewed
Recurrent Neural Network Exploration Strategies During Reinforcement Learning Depend on Network Capacity
Henrike Flimm, Deniz Tuzsus, Ioannis Pappas, Jan Peters
This study examines how RNN capacity affects exploration strategies in reinforcement learning, finding that higher capacity networks exhibit more human-like strategies but still differ in perseveration and switch rates.