Took a deeper dive on the (often neglected) discount factor in deep reinforcement learning (DRL).
What I learned from implementing Soft Actor Critic from scratch
Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
Quick guide to set up deep learning in the cloud
Policy optimization methods, Continued
Policy Gradient Methods for Reinforcement Learning with Function Approximation
DQN, Double DQN, and Dueling DQN
How to find the best way to start? Best resources?