Sign in
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents.
Quentin Delfosse
Sebastian Sztwiertnia
Wolfgang Stammer
Mark Rothermel
Kristian Kersting
Published in:
CoRR (2024)
Keyphrases
</>
reinforcement learning agents
dynamic environments
reinforcement learning
machine learning
multi agent
learning process
mobile robot
information extraction
evaluation function
state abstraction