Update Readme

README.md

@@ -6,6 +6,13 @@
 * Asynchronous N-Step Q-Learning
 * Asynchronous Advantage Actor Critic (A3C)
 
->Tested with both classical control tasks (CartPole, LunarLander) and Atari games.
+>Tested with both classical control tasks (CartPole) and Atari games.
 
->Try it out from ```main.py```!
+# Usage
+Detailed usage can be found in ```main.py```
+
+#References
+* [Human Level Control through Deep Reinforcement Learning](https://www.nature.com/nature/journal/v518/n7540/full/nature14236.html)
+* [Asynchronous Methods for Deep Reinforcement Learning](https://arxiv.org/abs/1602.01783)
+* [transedward/pytorch-dqn](https://github.com/transedward/pytorch-dqn)
+* [ikostrikov/pytorch-a3c](https://github.com/ikostrikov/pytorch-a3c)

main.py

@@ -129,10 +129,10 @@ if __name__ == '__main__':
     gym.logger.setLevel(logging.INFO)
 
     # async_cart_pole()
-    async_pixel_atari('PongNoFrameskip-v3')
     # dqn_cart_pole()
     # dqn_pixel_atari('BreakoutNoFrameskip-v3')
     # async_pixel_atari('BreakoutNoFrameskip-v3')
     # a3c_pixel_atari('BreakoutNoFrameskip-v3')
     # a3c_cart_pole()
+    async_pixel_atari('PongNoFrameskip-v3')
     # a3c_pixel_atari('PongNoFrameskip-v3')