Approximating a deep reinforcement learning docking agent using linear model trees

no code implementations • 1 Mar 2022 • Vilde B. Gjærum, Ella-Lovise H. Rørvik, Anastasios M. Lekkas

The two main benefits of the proposed approach are: a) LMTs are transparent which makes it possible to associate directly the outputs (control actions, in our case) with specific values of the input features, b) LMTs are computationally efficient and can provide information in real-time.

reinforcement-learning Reinforcement Learning (RL)

Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization

no code implementations • 1 Mar 2022 • Vilde B. Gjærum, Inga Strümke, Ole Andreas Alsos, Anastasios M. Lekkas

The main contributions of this work are (1) significantly improving both the accuracy and the build time of a greedy approach for building LMTs by introducing ordering of features in the splitting of the tree, (2) giving an overview of the characteristics of the seafarer/operator and the developer as two different end-users of the agent and receiver of the explanations, and (3) suggesting a visualization of the docking agent, the environment, and the feature attributions given by the LMT for when the developer is the end-user of the system, and another visualization for when the seafarer or operator is the end-user, based on their different characteristics.

Explainable artificial intelligence Reinforcement Learning (RL)