Login / Signup
Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects.
Siow Meng Low
Akshat Kumar
Scott Sanner
Published in:
CoRR (2023)
Keyphrases
</>
temporal patterns
reinforcement learning
learning algorithm
knowledge acquisition
markov decision processes
three dimensional
data structure
association rules
partially observable