Natural Gradient Deep Q-learning [article]

Ethan Knight, Osher Lerner
2018 arXiv   pre-print
We present a novel algorithm to train a deep Q-learning agent using natural-gradient techniques. We compare the original deep Q-network (DQN) algorithm to its natural-gradient counterpart, which we refer to as NGDQN, on a collection of classic control domains. Without employing target networks, NGDQN significantly outperforms DQN without target networks, and performs no worse than DQN with target networks, suggesting that NGDQN stabilizes training and can help reduce the need for additional
more » ... rparameter tuning. We also find that NGDQN is less sensitive to hyperparameter optimization relative to DQN. Together these results suggest that natural-gradient techniques can improve value-function optimization in deep reinforcement learning.
arXiv:1803.07482v2 fatcat:mr3kfotoozdgtflsqzhuzxgwsm