update readme and fix more folder and file names

Author: keon

1-grid-world/7-policy-pradient/environment.py renamed to 1-grid-world/7-policy-gradient/environment.py

@@ -6,7 +6,7 @@
 >
 > Maintainers - [Woongwon](https://github.com/dnddnjs), [Youngmoo](https://github.com/zzing0907), [Hyeokreal](https://github.com/Hyeokreal), [Uiryeong](https://github.com/wooridle), [Keon](https://github.com/keon)
 
-From the most basic algorithms to the more recent ones categorized as 'deep reinforcement learning', the examples are easy to read with comments.
+From the basics to deep reinforcement learning, this repo provides easy-to-read code examples. One file for each algorithm.
 Please feel free to create a [Pull Request](https://github.com/rlcode/reinforcement-learning/pulls), or open an [issue](https://github.com/rlcode/reinforcement-learning/issues)!
 
 ## Dependencies
@@ -27,25 +27,29 @@ pip install -r requirements.txt
 
 ## Table of Contents
 
-**Code 1** - Mastering the basics of reinforcement learning in the simplified world called "Grid World"
+**Basics** - Mastering the basics of reinforcement learning in the simplified world called "Grid World"
 
-- [Policy Iteration](./Code%201.%20Grid%20World/1.%20Policy%20Iteration)
-- [Value Iteration](./Code%201.%20Grid%20World/2.%20Value%20Iteration)
-- [Monte Carlo](./Code%201.%20Grid%20World/3.%20Monte-Carlo)
-- [SARSA](./Code%201.%20Grid%20World/4.%20SARSA)
-- [Q-Learning](./Code%201.%20Grid%20World/5.%20Q%20Learning)
-- [Deep Q Network](./Code%201.%20Grid%20World/6.%20DQN)
-- [Policy Gradient](./Code%201.%20Grid%20World/7.%20Policy%20Gradient)
+- [Policy Iteration](./1-grid-world/1-policy-iteration)
+- [Value Iteration](./1-grid-world/2-value-iteration)
+- [Monte Carlo](./1-grid-world/3-monte-carlo)
+- [SARSA](./1-grid-world/4-sarsa)
+- [Q-Learning](./1-grid-world/5-q-learning)
+- [Deep Q Network](./1-grid-world/6-deep-q-learning)
+- [Policy Gradient](./1-grid-world/7-policy-gradient)
 
-**Code 2** - Applying deep reinforcement learning on basic Cartpole game.
+**Intermediate** - Applying deep reinforcement learning on basic Cartpole game.
 
-- [Deep Q Network](./Code%202.%20Cartpole/1.%20DQN)
-- [Double Deep Q Network](./Code%202.%20Cartpole/2.%20Double%20DQN)
-- [Policy Gradient](./Code%202.%20Cartpole/3.%20Policy%20Gradient)
-- [Actor Critic (A2C)](./Code%202.%20Cartpole/4.%20Actor-Critic)
-- [Asynchronous Advantage Actor Critic (A3C)](./Code%202.%20Cartpole/5.%20A3C)
+- [Deep Q Network](./2-cartpole/1-dqn)
+- [Double Deep Q Network](./2-cartpole/2-double-dqn)
+- [Policy Gradient](./2-cartpole/3-policy-gradient)
+- [Actor Critic (A2C)](./2-cartpole/4-actor-critic)
+- [Asynchronous Advantage Actor Critic (A3C)](./2-cartpole/5-a3c)
 
-**Code 3** - Mastering Atari games with Deep Reinforcement Learning
+**Advanced** - Mastering Atari games with Deep Reinforcement Learning
 
-- [Breakout](./Code%203.%20Atari%20Game/1.%20Breakout) - [DQN](https://github.com/rlcode/reinforcement-learning/tree/master/Code%203.%20Atari%20Game/1.%20Breakout), PG, [A3C](https://github.com/rlcode/reinforcement-learning/tree/master/Code%203.%20Atari%20Game/3.%20A3C)
-- [Pong](./Code%203.%20Atari%20Game/2.%20Pong) - DQN, PG, A3C
+- **Breakout** - [DQN](./3-atari/1-breakout/breakout_dqn.py), [DDQN](./3-atari/1-breakout/breakout_ddqn.py) [Dueling DDQN](./3-atari/1-breakout/breakout_ddqn.py) [A3C](./3-atari/1-breakout/breakout_a3c.py)
+- **Pong** - [Policy Gradient](./3-atari/2-pong/pong_pg.py), [A3C](./3-atari/2-pong/pong-a3c.py)
+
+**ETC** - [WIP]
+
+- Mountain Car - [DQN]()