Search Results for author:
Found 2 papers, 0 papers with code
Towards Characterizing Divergence in Deep Q-Learning
Deep Q-Learning (DQL), a family of temporal difference algorithms for control, employs three techniques collectively known as the `deadly triad' in reinforcement learning: bootstrapping, off-policy learning, and function approximation.
Natural Gradient Deep Q-learning
We present a novel algorithm to train a deep Q-learning agent using natural-gradient techniques.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
