Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space.

Sanyam Vyas Chris Hicks Vasilios Mavroudis

Published in: CoRR (2024)

Keyphrases

reinforcement learning
neural network
space time
satisfiability problem
multi agent
genetic algorithm
search space
dynamic programming
state space
markov decision processes
function approximation
risk management
hidden structure
fitted q iteration