2 papers
cs.RO2021
Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learning
Sindre Benjamin Remman, Inga Strümke, Anastasios M. Lekkas
We investigate the effect of including domain knowledge about a robotic system's causal relations when generating explanations. To this end, we compare two methods from explainable…
cs.RO2021
Robotic Lever Manipulation using Hindsight Experience Replay and Shapley Additive Explanations
Sindre Benjamin Remman, Anastasios M. Lekkas
This paper deals with robotic lever control using Explainable Deep Reinforcement Learning. First, we train a policy by using the Deep Deterministic Policy Gradient algorithm and th…