shanhaoyu / deep-q-network-breakout Goto Github PK
View Code? Open in Web Editor NEWThis is an implementation of Deep Q Learning (DQN) playing Breakout from OpenAI's gym with Keras.
This is an implementation of Deep Q Learning (DQN) playing Breakout from OpenAI's gym with Keras.
(venv_deep-q-network-breakout) (base) w-mbas-9293:Deep-Q-Network-Breakout jesusramos$ python main.py --train_dqn --dueling True
/Users/rams/AIs/venv_deep-q-network-breakout/lib/python3.5/site-packages/gym/logger.py:30: UserWarning: WARN: gym.spaces.Box autodetected dtype as <class 'numpy.uint8'>. Please provide explicit dtype.
warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow'))
Using TensorFlow backend.
2019-02-07 14:45:28.417123: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Traceback (most recent call last):
File "main.py", line 39, in
run(args)
File "main.py", line 28, in run
agent = Agent_DQN(env, args)
File "/Users/jesusramos/AIs/Deep-Q-Network-Breakout/agent_dir/agent_dqn.py", line 91, in init
self.q_network = self.build_network()
File "/Users/rams/AIs/Deep-Q-Network-Breakout/agent_dir/agent_dqn.py", line 170, in build_network
output_shape = self.num_actions)
TypeError: 'module' object is not callable
Thank you very much for sharing your wonderful project!
I'd like to train my own agents with your code and I am curious how long you trained the model shared in your google drive. How many episodes and frames did you train it? On which hardware did you train it (GPU/RAM)? How many hours did the training take?
The agent should follow the same policy in both training and testing process , and I check the code, and run all three methods of deep Q-learning, but the training reward of an episode are always below 15, but the testing reward can be above 60, I can't really explain that
Thank you very much sharing the repo. I have tried to use your model but I am getting the following error.
tensorflow.python.framework.errors_impl.UnknownError: FindFirstFile failed for: ./data/Breakout/dqn_300.h5 : The directory name is invalid.
; Unknown error
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.