https://github.com/carpedm20/NAF-tensorflow

"Continuous Deep Q-Learning with Model-based Acceleration" in TensorFlow
https://github.com/carpedm20/NAF-tensorflow

continuous-rl deep-learning deep-reinforcement-learning gym reinforcement-learning tensorflow

Last synced: about 2 months ago
JSON representation

"Continuous Deep Q-Learning with Model-based Acceleration" in TensorFlow

• Host: GitHub
• URL: https://github.com/carpedm20/NAF-tensorflow
• Owner: carpedm20
• License: mit
• Created: 2016-07-06T16:25:42.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2018-07-20T23:40:54.000Z (almost 6 years ago)
• Last Synced: 2024-01-26T22:53:57.920Z (5 months ago)
• Topics: continuous-rl, deep-learning, deep-reinforcement-learning, gym, reinforcement-learning, tensorflow
• Language: Python
• Homepage:
• Size: 492 KB
• Stars: 193
• Watchers: 17
• Forks: 61
• Open Issues: 7
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-model-compression - NAF-tensorflow - Learning with Model-based Acceleration" in TensorFlow; (PROJECTS / 2023)

README

        
# Normalized Advantage Functions (NAF) in TensorFlow

TensorFlow implementation of [Continuous Deep q-Learning with Model-based Acceleration](http://arxiv.org/abs/1603.00748).

![algorithm](https://github.com/carpedm20/naf-tensorflow/blob/master/assets/algorithm.png)

## Requirements

- Python 2.7

- [gym](https://github.com/openai/gym)

- [TensorFlow](https://www.tensorflow.org/) 0.9+

## Usage

First, install prerequisites with:

    $ pip install tqdm gym[all]

To train a model for an environment with a continuous action space:

    $ python main.py --env_name=Pendulum-v0 --is_train=True

    $ python main.py --env_name=Pendulum-v0 --is_train=True --display=True

To test and record the screens with gym:

    $ python main.py --env_name=Pendulum-v0 --is_train=False

    $ python main.py --env_name=Pendulum-v0 --is_train=False --display=True

## Results

Training details of `Pendulum-v0` with different hyperparameters.

    $ python main.py --env_name=Pendulum-v0 # dark green

    $ python main.py --env_name=Pendulum-v0 --action_fn=tanh # light green

    $ python main.py --env_name=Pendulum-v0 --use_batch_norm=True # yellow

    $ python main.py --env_name=Pendulum-v0 --use_seperate_networks=True # green

![Pendulum-v0_2016-07-15](https://github.com/carpedm20/naf-tensorflow/blob/master/assets/Pendulum-v0_2016-07-15.png)

## References

- [rllab](https://github.com/rllab/rllab.git)

- [keras implementation](https://gym.openai.com/evaluations/eval_CzoNQdPSAm0J3ikTBSTCg)

## Author

Taehoon Kim / [@carpedm20](http://carpedm20.github.io/)