Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects.

Siow Meng Low Akshat Kumar Scott Sanner

Published in: ICAPS (2023)

Keyphrases

temporal patterns
reinforcement learning
information retrieval
knowledge acquisition
learning algorithm
contextual information
data sets
data mining
multi dimensional
information retrieval systems
np complete
optimal policy
temporal constraints
temporal data mining