When drawing 1,000 z from the priorp(z)of the latent space learned by PLAS, only4%of the samples are decoded as high-return actions, while inLAPO,45%ofthedecoded actions arehigh-return actions.

Recurrent spiking neural networks (RSNNs) hold great potential for advancing artificial general intelligence, as they draw inspiration from the biological nervous system and show promise in modeling complex dynamics.

Human motor control remains agile and robust despite limited sensory information for feedback, a property attributed to the body's ability to perform morphological computation through muscle coordination with variable impedance. However, it remains unclear how such low-level mechanical computation reduces the control requirements of the high-level controller. In this study, we implement a hierarchical controller consisting of a high-level neural network trained by reinforcement learning and a low-level variable-impedance muscle coor dination model with mono- and biarticular muscles in monoped locomotion task. We systematically restrict the high-level controller by varying the control frequency and by introducing biologically inspired observation conditions: delayed, partial, and substituted observation. Under these conditions, we evaluate how the low-level variable-impedance muscle coordination contributes to learning process of high-level neural network. The results show that variable-impedance muscle coordination enables stable locomotion even under slow-rate control frequency and limited observation conditions. These findings demonstrate that the morphological computation of muscle coordination effectively offloads high-frequency feedback of the high-level controller and provide a design principle for the controller in motor control.

Reinforcement learning has recently enabled impressive locomotion capabilities on legged robots; however, most policy architectures remain morphology- and symmetry-agnostic, leading to inefficient training and limited generalization. This work introduces MS-PPO, a morphological-symmetry-equivariant policy learning framework that encodes robot kinematic structure and morphological symmetries directly into the policy network. We construct a morphology-informed graph neural architecture that is provably equivariant with respect to the robot's morphological symmetry group actions, ensuring consistent policy responses under symmetric states while maintaining invariance in value estimation. This design eliminates the need for tedious reward shaping or costly data augmentation, which are typically required to enforce symmetry. We evaluate MS-PPO in simulation on Unitree Go2 and Xiaomi CyberDog2 robots across diverse locomotion tasks, including trotting, pronking, slope walking, and bipedal turning, and further deploy the learned policies on hardware. Extensive experiments show that MS-PPO achieves superior training stability, symmetry generalization ability, and sample efficiency in challenging locomotion tasks, compared to state-of-the-art baselines. These findings demonstrate that embedding both kinematic structure and morphological symmetry into policy learning provides a powerful inductive bias for legged robot locomotion control. Our code will be made publicly available at https://lunarlab-gatech.github.io/MS-PPO/.

This online learning process is however fundamentally slow.