An Interpretable Neural Control Network With Adaptable Online Learning for Sample Efficient Robot Locomotion Learning

Robot locomotion learning using reinforcement learning suffers from training sample inefficiency and exhibits the non-interpretable/closed-box nature. Thus, this work presents a novel SME-Adaptable Gradient-weighting Online Learning (AGOL) to address such problems. First, sequential motion executor (SME) is a three-layer interpretable neural network, where the first produces the sequentially propagating hidden states, the second constructs the corresponding triangular bases with minor non-neighbor interference, and the third maps the bases to the motor commands. Second, the AGOL algorithm prioritizes the update of the parameters with high relevance score, allowing the learning to focus more on the highly relevant ones. Thus, these two components lead to an analyzable framework, where each sequential hidden state/basis represents the learned key poses/robot configuration. Compared to state-of-the-art methods, the SME-AGOL requires 40% fewer samples and receives 150% higher final reward/locomotion performance on a simulated hexapod robot, while taking merely 10 min of learning time from scratch on a physical hexapod robot. Taken together, this work not only proposes the SME-AGOL for sample efficient and understandable locomotion learning but also emphasizes the potential exploitation of interpretability for improving sample efficiency and learning performance.