https://github.com/amifunny/reinforce_adventure

This Repository contains my implementation of popular algorithms on popular environments.
https://github.com/amifunny/reinforce_adventure

actor-critic bandit ddpg dqn dqn-tensorflow gym openai reinforcement-learning reinforcement-learning-algorithms rl

Last synced: 3 months ago
JSON representation

This Repository contains my implementation of popular algorithms on popular environments.

• Host: GitHub
• URL: https://github.com/amifunny/reinforce_adventure
• Owner: amifunny
• Created: 2020-05-23T08:57:54.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2020-07-16T17:46:38.000Z (almost 5 years ago)
• Last Synced: 2025-03-19T22:53:11.359Z (3 months ago)
• Topics: actor-critic, bandit, ddpg, dqn, dqn-tensorflow, gym, openai, reinforcement-learning, reinforcement-learning-algorithms, rl
• Language: Python
• Size: 1.18 MB
• Stars: 5
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        

# Reinforce Adventure

This Repository contains my implementation of popular algorithms on popular environments.

Repository contains code for - 

##  Inverted Pendulum Problem

- [DDPG ( Deep Deterministic Policy Gradient )](https://github.com/amifunny/Reinforce_Adventure/blob/master/DDPG_Keras_Example_wtih_Pendulum.ipynb)

	Also on [official keras-examples](https://keras.io/examples/rl/ddpg_pendulum/)

![GIF for Pendulum](gifs/pendulum.gif)

## Cartpole Problem

	

- [Actor-Critic](https://github.com/amifunny/Reinforce_Adventure/blob/master/ACTOR_CRITIC.py)

-	[Monte Carlo Method](https://github.com/amifunny/Reinforce_Adventure/blob/master/Monte_Carlo_Method.py)

-	[PPO ( Proximal Policy Optimization )](https://github.com/amifunny/Reinforce_Adventure/blob/master/PPO_Algorithms.py)

-	[Q-Learning with Neural Net](https://github.com/amifunny/Reinforce_Adventure/blob/master/Q_Learning_CartPole.py)

-	[Vanilla Policy Gradient](https://github.com/amifunny/Reinforce_Adventure/blob/master/Vanilla_policy_Gradient.py)

![GIF for Cartpole](gifs/cartpole.gif)

## Lunar Lander

- [Actor-Critic](https://github.com/amifunny/Reinforce_Adventure/blob/master/Moon_Lander_Discrete.py)

 

![GIF for LunarLander](gifs/lunar_lander.gif)

## Mountain Car

  - [Q-Learning with Neural Net](https://github.com/amifunny/Reinforce_Adventure/blob/master/Q_Learning_Mountain_CAR.py)

  

   ![GIF for MountainCar](gifs/mountain.gif)

   

## Slot Machine Bandit problem

- [E-greedy & Thompson Sampling](https://github.com/amifunny/Reinforce_Adventure/blob/master/Multi_Armed_Bandits.py)

![Graph E-greedy vs Thompson](gifs/MultiArmedBandit.png)