Login / Signup
DSMC Evaluation Stages: Fostering Robust and Safe Behavior in Deep Reinforcement Learning.
Timo P. Gros
Daniel Höller
Jörg Hoffmann
Michaela Klauck
Hendrik Meerkamp
Verena Wolf
Published in:
QEST (2021)
Keyphrases
</>
reinforcement learning
computationally efficient
machine learning
markov decision processes
decision making
multi agent
optimal policy
multistage
knowledge building
gold standard
parameter tuning
robust estimation
evaluation process
behavior patterns