GRP Model for Sensorimotor Learning
This addresses sensorimotor learning for robotics or neuroscience applications, but it is incremental as it builds on existing imitation learning and modular approaches.
The paper tackles the problem of learning from complex demonstrations with multiple strategies by developing the Generator and Responsibility Predictor (GRP) model, which automatically learns and switches between sub-task policies from unsegmented demonstrations, and it successfully transfers swing leg control from the brain to the spinal cord in a physiological neural network.
Learning from complex demonstrations is challenging, especially when the demonstration consists of different strategies. A popular approach is to use a deep neural network to perform imitation learning. However, the structure of that deep neural network has to be ``deep" enough to capture all possible scenarios. Besides the machine learning issue, how humans learn in the sense of physiology has rarely been addressed and relevant works on spinal cord learning are rarer. In this work, we develop a novel modular learning architecture, the Generator and Responsibility Predictor (GRP) model, which automatically learns the sub-task policies from an unsegmented controller demonstration and learns to switch between the policies. We also introduce a more physiological based neural network architecture. We implemented our GRP model and our proposed neural network to form a model the transfers the swing leg control from the brain to the spinal cord. Our result suggests that by using the GRP model the brain can successfully transfer the target swing leg control to the spinal cord and the resulting model can switch between sub-control policies automatically.