Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents

1 code implementation • 11 Jan 2024 • Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, Kristian Kersting

Unfortunately, the black-box nature of deep neural networks impedes the inclusion of domain experts for inspecting the model and revising suboptimal policies.

reinforcement-learning Reinforcement Learning (RL)