dongminlee94 / Samsung-DRL-Code

A repository for implementation of deep reinforcement learning lectured at Samsung

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Deep Reinforcement Learning, Summer 2019 (Samsung)

This repository contains codes for Deep Reinforcement Learning (DRL) algorithms with PyTorch (v0.4.1). It also provides lecture slides that explain codes in detail.

The agents with the DRL algorithms have been implemented and trained using classic control environments in OpenAI Gym.

Table of Contents

00. Prerequisite

  1. Install from Anaconda to OpenAI Gym (Window Ver. & MacOS Ver.)
  2. Numpy

01. Deep Learning with PyTorch

02. Deep Q-Network (DQN) & Double DQN (DDQN)

03. Advantage Actor-Critic (A2C) & Deep Deterministic Policy Gradient (DDPG)

  1. A2C

  2. DDPG

04. Trust Region Policy Optimization (TRPO) & Proximal Policy Optimization (PPO)

  1. TRPO

  2. TRPO + GAE

  3. PPO

  4. PPO + GAE

05. Soft Actor-Critic (SAC)

Learning curve

CartPole

Pendulum

Paper

Reference

About

A repository for implementation of deep reinforcement learning lectured at Samsung

License:MIT License


Languages

Language:Python 100.0%