Exercise 6.4.1

Deep Q-networks: target network against the deadly triad

Reinforcement Learning › Exercises › Lecture 6 · Function Approximation › 6.4 Convergence, divergence and experience replay
EasyMultiple choice

Deep Q-Networks (DQN) introduced several key innovations to stabilize the learning process in the presence of the deadly triad (function approximation, bootstrapping, and off-policy learning). Which of the following techniques are employed in DQN to address these challenges?