Deep Reinforcement Learning

In Progress

This blog will only contain pseudocodes and important pointers for my reference.

Deep Q Network (DQN)

Double DQN

Actor-Critic Network

Deterministic Policy Gradient (DPG)

Deep Deterministic Policy Gradient (DDPG)

Advantage Actor-Critic Network (A2C)

Asynchronous Advantage Actor-Critic Network (A3C)

Proximal Policy Optimization (PPO)