An Ergodic Measure for Active Learning From Equilibrium
This work addresses the challenge of balancing exploration and task execution in robotics, offering a method that is incremental by building on ergodic exploration and hybrid systems theory.
The paper tackles the problem of integrating stability into active data generation for robotic systems by developing KL-Ergodic Exploration from Equilibrium (KL-E^3), which enables robots to maintain task performance while exploring to collect informative data for learning tasks like Bayesian optimization and reinforcement learning, resulting in smooth control signals and real-time applicability.
This paper develops KL-Ergodic Exploration from Equilibrium ($\text{KL-E}^3$), a method for robotic systems to integrate stability into actively generating informative measurements through ergodic exploration. Ergodic exploration enables robotic systems to indirectly sample from informative spatial distributions globally, avoiding local optima, and without the need to evaluate the derivatives of the distribution against the robot dynamics. Using hybrid systems theory, we derive a controller that allows a robot to exploit equilibrium policies (i.e., policies that solve a task) while allowing the robot to explore and generate informative data using an ergodic measure that can extend to high-dimensional states. We show that our method is able to maintain Lyapunov attractiveness with respect to the equilibrium task while actively generating data for learning tasks such, as Bayesian optimization, model learning, and off-policy reinforcement learning. In each example, we show that our proposed method is capable of generating an informative distribution of data while synthesizing smooth control signals. We illustrate these examples using simulated systems and provide simplification of our method for real-time online learning in robotic systems.