Skip to content
conftrace_

normalized advantage function

2 papers

Explore in graph

Also known as

NAF

Co-occurring keywords · papers mentioning both

continuous control (2) deep reinforcement learning (2) model-based acceleration (1) q-function approximation (1) deep q-learning (1) experience replay (1) robotic control (1) quadratic approximation (1) model-based reinforcement learning (1) optimal control (1)

Papers

Continuous Deep Q-Learning in Optimal Control Problems: Normalized Advantage Functions Analysis NeurIPS 2022 Continuous Deep Q-Learning with Model-based Acceleration ICML 2016