add: br

Author: archsyscall

README.md

@@ -21,6 +21,8 @@
 - [TD3](#td3)
 - [SAC](#sac)
 
+<hr>
+
 <a name='dqn'></a>
 
 ### DQN
@@ -71,8 +73,11 @@ class ReplayBuffer:
 $ python DQN/DQN_Discrete.py
 ```
 
+<hr>
+
 <a name='drqn'></a>
 
+
 ### DRQN
 
 **Paper** [Deep Recurrent Q-Learning for Partially Observable MDPs](https://arxiv.org/abs/1507.06527)<br>
@@ -85,8 +90,11 @@ $ python DQN/DQN_Discrete.py
 $ python DRQN/DRQN_Discrete.py
 ```
 
+<hr>
+
 <a name='double_dqn'></a>
 
+
 ### DoubleDQN
 
 **Paper** [Deep Reinforcement Learning with Double Q-learning](https://arxiv.org/abs/1509.06461)<br>
@@ -99,6 +107,8 @@ $ python DRQN/DRQN_Discrete.py
 $ python DoubleQN/DoubleDQN_Discrete.py
 ```
 
+<hr>
+
 <a name='dueling_dqn'></a>
 
 ### DoubleDQN
@@ -113,6 +123,8 @@ $ python DoubleQN/DoubleDQN_Discrete.py
 $ python DuelingDQN/DuelingDQN_Discrete.py
 ```
 
+<hr>
+
 <a name='a2c'></a>
 
 ### A2C
@@ -130,6 +142,8 @@ $ python A2C/A2C_Discrete.py
 $ python A2C/A2C_Continuous.py
 ```
 
+<hr>
+
 <a name='a3c'></a>
 
 ### A3C
@@ -147,6 +161,8 @@ $ python A3C/A3C_Discrete.py
 $ python A3C/A3C_Continuous.py
 ```
 
+<hr>
+
 <a name='ppo'></a>
 
 ### PPO
@@ -164,6 +180,8 @@ $ python PPO/PPO_Discrete.py
 $ python PPO/PPO_Continuous.py
 ```
 
+<hr>
+
 <a name='trpo'></a>
 
 ### TRPO
@@ -177,6 +195,8 @@ $ python PPO/PPO_Continuous.py
 # NOTE: Not yet implemented!
 ```
 
+<hr>
+
 <a name='ddpg'></a>
 
 ### DDPG
@@ -190,6 +210,8 @@ $ python PPO/PPO_Continuous.py
 # NOTE: Not yet implemented!
 ```
 
+<hr>
+
 <a name='td3'></a>
 
 ### TD3
@@ -203,6 +225,8 @@ $ python PPO/PPO_Continuous.py
 # NOTE: Not yet implemented!
 ```
 
+<hr>
+
 <a name='sac'></a>
 
 ### SAC
@@ -217,6 +241,8 @@ $ python PPO/PPO_Continuous.py
 # NOTE: Not yet implemented!
 ```
 
+<hr>
+
 ## Reference
 
 - https://github.com/carpedm20/deep-rl-tensorflow