Interactive Learning with Corrective Feedback for Policies based on Deep Neural Networks
This addresses the problem of high data demands in training policies for physical systems, enabling non-expert humans to shape policies interactively, though it is incremental as it builds on the existing COACH framework.
The paper tackles the data inefficiency of deep reinforcement learning by introducing Deep COACH, an interactive method that uses human corrective feedback to train deep neural network policies without a reward function. It demonstrates faster learning than DRL in simulated and real robot tasks, such as Car Racing and Cart-Pole, with state spaces of varying dimensions.
Deep Reinforcement Learning (DRL) has become a powerful strategy to solve complex decision making problems based on Deep Neural Networks (DNNs). However, it is highly data demanding, so unfeasible in physical systems for most applications. In this work, we approach an alternative Interactive Machine Learning (IML) strategy for training DNN policies based on human corrective feedback, with a method called Deep COACH (D-COACH). This approach not only takes advantage of the knowledge and insights of human teachers as well as the power of DNNs, but also has no need of a reward function (which sometimes implies the need of external perception for computing rewards). We combine Deep Learning with the COrrective Advice Communicated by Humans (COACH) framework, in which non-expert humans shape policies by correcting the agent's actions during execution. The D-COACH framework has the potential to solve complex problems without much data or time required. Experimental results validated the efficiency of the framework in three different problems (two simulated, one with a real robot), with state spaces of low and high dimensions, showing the capacity to successfully learn policies for continuous action spaces like in the Car Racing and Cart-Pole problems faster than with DRL.