RL_Algorithms

Provides various reinforcement learning algorithms.

Created for personal study purposes.

The links below have also been added, so please refer to them if necessary.

DQN

CartPole DQN

https://blog.naver.com/jk96491/221846530113 - DQN Concept description

PPO (Proximal Policy Optimization)

Pendulum-v0

https://blog.naver.com/jk96491/221992903677 - PPO Proposal Background

https://blog.naver.com/jk96491/221993897641 - PPO apply

DDPG

CartPole DDPG

https://blog.naver.com/jk96491/221848853398 - DDPG Concept description

REINFORCE, REINFORCE-Baseline

CartPole REINFORCE, CartPole REINFORCE-Baseline

https://blog.naver.com/jk96491/221964240769 - REINFORCE Concept description

https://blog.naver.com/jk96491/221965998206 - REINFORCE Baseline Concept description

https://blog.naver.com/jk96491/221851464029 - CartPole apply

Actor-critic

Pendulum-v0

https://blog.naver.com/jk96491/221972163239 - Advantage Actor Critic(A2C) Concept description

A3C(Asynchronous Advantage Actor-Critic)

Pendulum-v0

https://blog.naver.com/jk96491/221990932299 - A3C Concept description