DQN-tensorflow writeup

README.md

DQN-tensorflow

First, clone the project:

git clone https://github.com/devsisters/DQN-tensorflow/
cd DQN-tensorflow

To train a model for Breakout:

python main.py --env_name=Breakout-v0 --is_train=True
python main.py --env_name=Breakout-v0 --is_train=True --display=True

To test and record the screen with gym (the repo already contains checkpoint):

python main.py --is_train=False
python main.py --is_train=False --display=True

The best model can be obtained for 10M iteration with:

python main.py --env_name=Breakout-v0 --is_train=True --model=m2

I cannot reproduce:

i get a MemoryError on:

Traceback (most recent call last): File "main.py", line 63, in <module> tf.app.run() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 30, in run sys.exit(main(sys.argv)) File "main.py", line 50, in main agent = Agent(config, env, sess) File "/env/deep27/DQN-tensorflow/dqn/agent.py", line 22, in __init__ self.memory = ReplayMemory(self.config, self.model_dir) File "/env/deep27/DQN-tensorflow/dqn/replay_memory.py", line 18, in __init__ self.screens = np.empty((self.memory_size, config.screen_height, config.screen_width), dtype = np.float16) MemoryError

@Sessa93 You need a bigger memory to run this model. My server has 32GB memory but 16GB should be enough. How much memory do you have?