Mode-Constrained Exploration for Model-Based Reinforcement Learning
Aidan ScannellSep 24, 2022
reinforcement-learning machine-learning gaussian-processes optimal-control robotics python TensorFlow GPflow research
My research interests include model-based reinforcement learning, probabilistic machine learning (gaussian processes, Bayesian neural networks, approximate Bayesian inference, etc), learning-based control and optimal control.
We present a model-based RL algorithm that constrains training to a single dynamic mode with high probability. This is a difficult problem because the mode constraint is a hidden variable associated with the environment’s dynamics. As such, it is 1) unknown a priori and 2) we do not observe its output from the environment, so cannot learn it with supervised learning.
Aidan Scannell, Carl Henrik Ek, Arthur Richards