Shielded Deep Reinforcement Learning for Complex Spacecraft Tasking.

Robert Reed Hanspeter Schaub Morteza Lahijanian

Published in: CoRR (2024)

Keyphrases

reinforcement learning
databases
real world
complex data
function approximation
machine learning
social networks
high level
evolutionary algorithm
dynamic programming
least squares
optimal policy
complex systems
temporal difference
complex domains
mission planning