Search Results for author:
Found 7 papers, 0 papers with code
Discovering Behavioral Modes in Deep Reinforcement Learning Policies Using Trajectory Clustering in Latent Space
In this paper, we introduce a new approach for investigating the behavior modes of DRL policies, which involves utilizing dimensionality reduction and trajectory clustering in the latent space of neural networks.
Approximating a deep reinforcement learning docking agent using linear model trees
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.
Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization
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)
Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learning
This partial causal ordering defines the causal relations between the features, and we specify this using domain knowledge about the lever control task.
Explainable artificial intelligence
Reinforcement Learning (RL)
Robotic Lever Manipulation using Hindsight Experience Replay and Shapley Additive Explanations
To explain the decisions of the policy we use the SHAP method to create an explanation model based on the episodes done in the real-world environment.
MPC-based Reinforcement Learning for a Simplified Freight Mission of Autonomous Surface Vehicles
In this work, we propose a Model Predictive Control (MPC)-based Reinforcement Learning (RL) method for Autonomous Surface Vehicles (ASVs).
Reinforcement Learning based on Scenario-tree MPC for ASVs
A scenario-tree robust MPC is used to handle potential failures of the ship thrusters.
