Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/devsisters/DQN-tensorflow
Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning
https://github.com/devsisters/DQN-tensorflow
Last synced: about 2 months ago
JSON representation
Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning
- Host: GitHub
- URL: https://github.com/devsisters/DQN-tensorflow
- Owner: devsisters
- License: mit
- Created: 2016-05-15T11:33:47.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2019-04-18T18:36:45.000Z (over 5 years ago)
- Last Synced: 2024-10-15T12:41:27.771Z (about 2 months ago)
- Language: Python
- Homepage:
- Size: 28.9 MB
- Stars: 2,476
- Watchers: 146
- Forks: 764
- Open Issues: 38
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-tensorflow - DQN-tensorflow - TensorFlow implementation of DeepMind's 'Human-Level Control through Deep Reinforcement Learning' with OpenAI Gym by Devsisters.com (Models/Projects)
- Awesome-TensorFlow-Chinese - DQN-tensorflow - TensorFlow implementation of DeepMind's 'Human-Level Control through Deep Reinforcement Learning' with OpenAI Gym by Devsisters.com (模型项目 / 微信群)
- Github-Repositories - DQN-tensorflow
- awesome-tensorflow - DQN-tensorflow - TensorFlow implementation of DeepMind's 'Human-Level Control through Deep Reinforcement Learning' with OpenAI Gym by Devsisters.com (Models/Projects)
- fucking-awesome-tensorflow - DQN-tensorflow - TensorFlow implementation of DeepMind's 'Human-Level Control through Deep Reinforcement Learning' with OpenAI Gym by Devsisters.com (Models/Projects)
README
# Human-Level Control through Deep Reinforcement Learning
Tensorflow implementation of [Human-Level Control through Deep Reinforcement Learning](http://home.uchicago.edu/~arij/journalclub/papers/2015_Mnih_et_al.pdf).
This implementation contains:
1. Deep Q-network and Q-learning
2. Experience replay memory
- to reduce the correlations between consecutive updates
3. Network for Q-learning targets are fixed for intervals
- to reduce the correlations between target and predicted Q-values
## Requirements
- Python 2.7 or Python 3.3+
- [gym](https://github.com/openai/gym)
- [tqdm](https://github.com/tqdm/tqdm)
- [SciPy](http://www.scipy.org/install.html) or [OpenCV2](http://opencv.org/)
- [TensorFlow 0.12.0](https://github.com/tensorflow/tensorflow/tree/r0.12)
## Usage
First, install prerequisites with:
$ pip install tqdm gym[all]
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:
$ python main.py --is_train=False
$ python main.py --is_train=False --display=True
## Results
Result of training for 24 hours using GTX 980 ti.
## Simple Results
Details of `Breakout` with model `m2`(red) for 30 hours using GTX 980 Ti.
Details of `Breakout` with model `m3`(red) for 30 hours using GTX 980 Ti.
## Detailed Results
**[1] Action-repeat (frame-skip) of 1, 2, and 4 without learning rate decay**
**[2] Action-repeat (frame-skip) of 1, 2, and 4 with learning rate decay**
**[1] & [2]**
**[3] Action-repeat of 4 for DQN (dark blue) Dueling DQN (dark green) DDQN (brown) Dueling DDQN (turquoise)**
The current hyper parameters and gradient clipping are not implemented as it is in the paper.
**[4] Distributed action-repeat (frame-skip) of 1 without learning rate decay**
**[5] Distributed action-repeat (frame-skip) of 4 without learning rate decay**
## References
- [simple_dqn](https://github.com/tambetm/simple_dqn.git)
- [Code for Human-level control through deep reinforcement learning](https://sites.google.com/a/deepmind.com/dqn/)
## License
MIT License.