no code implementations • 20 Mar 2018 • Ethan Knight, Osher Lerner
We present a novel algorithm to train a deep Q-learning agent using natural-gradient techniques.
no code implementations • 21 Mar 2019 • Joshua Achiam, Ethan Knight, Pieter Abbeel
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.