https://github.com/bhanuvikasr/deep-rl-torcs
Autonomous Navigation using Deep Reinforcement Learning
https://github.com/bhanuvikasr/deep-rl-torcs
actor-critic deep-q-network deep-reinforcement-learning policy-gradient
Last synced: about 2 months ago
JSON representation
Autonomous Navigation using Deep Reinforcement Learning
- Host: GitHub
- URL: https://github.com/bhanuvikasr/deep-rl-torcs
- Owner: bhanuvikasr
- Created: 2017-05-22T23:09:03.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2017-05-23T00:34:24.000Z (over 8 years ago)
- Last Synced: 2025-04-13T11:52:34.839Z (6 months ago)
- Topics: actor-critic, deep-q-network, deep-reinforcement-learning, policy-gradient
- Language: Python
- Homepage:
- Size: 14.4 MB
- Stars: 24
- Watchers: 5
- Forks: 12
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Deep Reinforcement Learning approach to Autonomous Navigation
## Abstract
In this project we use state-of-the-art RL algorithms to explore the problem of Autonomous Navigation. Specifically, we employ DeepMind's DDPG (Deep Deterministic Policy Gradient) algorithm to learn an agent for navigation in TORCS simulation environment.
## Simulation Environment
We use TORCS([gym_torcs](https://github.com/ugo-nama-kun/gym_torcs)) simulation environment for this task.
## Demo
### Training
### Testing
## Installation Dependencies:
* Python 2.7
* Keras 1.1.0
* Tensorflow r0.10
* [gym_torcs](https://github.com/ugo-nama-kun/gym_torcs)
## How to Run?
```
git clone https://github.com/bhanuvikasr/Deep-RL-TORCS.git
cd DDPG-Keras-Torcs
cp *.* ~/gym_torcs
cd ~/gym_torcs
python ddpg.py
```
(Change the flag **train_indicator**=1 in ddpg.py if you want to train the network)
## Credits
Thanks to [Yanpanlau](https://github.com/yanpanlau/DDPG-Keras-Torcs.git)