https://github.com/jimkon/Deep-Reinforcement-Learning-in-Large-Discrete-Action-Spaces
Implementation of the algorithm in Python 3, TensorFlow and OpenAI Gym
https://github.com/jimkon/Deep-Reinforcement-Learning-in-Large-Discrete-Action-Spaces
ddpg deep-reinforcement-learning discrete-actions wolpertinger
Last synced: 6 months ago
JSON representation
Implementation of the algorithm in Python 3, TensorFlow and OpenAI Gym
- Host: GitHub
- URL: https://github.com/jimkon/Deep-Reinforcement-Learning-in-Large-Discrete-Action-Spaces
- Owner: jimkon
- License: mit
- Created: 2017-11-25T14:41:04.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2018-03-01T15:47:02.000Z (over 7 years ago)
- Last Synced: 2024-11-04T18:45:20.380Z (11 months ago)
- Topics: ddpg, deep-reinforcement-learning, discrete-actions, wolpertinger
- Language: Python
- Size: 208 MB
- Stars: 173
- Watchers: 9
- Forks: 54
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Deep-Reinforcement-Learning-in-Large-Discrete-Action-Spaces
Link to [paper](https://arxiv.org/abs/1512.07679)
Implementation of the algorithm in Python 3, TensorFlow and OpenAI Gym.
This paper introduces Wolpertinger training algorithm that extends the Deep Deterministic Policy Gradient training algorithm introduced in [this](https://arxiv.org/abs/1509.02971) paper.
I used and extended **stevenpjg**'s implementation of **DDPG** algorithm found [here](https://github.com/stevenpjg/ddpg-aigym) licensed under the MIT license.
Master is currently **only for continuous action spaces**.
The branch discrete-and-continuous provides the ability to use the discrete environments of the gym.