# dueling-DQN-pytorch

**Repository Path**: ChenGouXiang/dueling-DQN-pytorch

## Basic Information

- **Project Name**: dueling-DQN-pytorch
- **Description**: very easy implementation of dueling DQN in pytorch
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 2
- **Forks**: 1
- **Created**: 2019-11-20
- **Last Updated**: 2022-08-04

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# dueling-DQN-pytorch
very easy implementation of dueling DQN in pytorch

all things are in one file, easily to follow~~

![Architecture](./dueling-DQN.png)

## requirement 

- tensorflow (for tensorboard logging)
- pytorch (>=1.0, 1.0.1 used in my experiment)
- gym
- [ViZDoom](https://github.com/mwydmuch/ViZDoom)


## CartPole-v0

for training ddqn in CartPole, just run 

```
python ddqn.py
```

common, no description~

in CartPole-v0 the network will convergence to 200 episode reward very quickly~~
## Visual doom

for training ddqn in Visual doom, just run
```
python visual_doom.py
```

for testing ddqn in Visual doom, just run
```
python visual_doom_test.py
```

use the [basic](https://github.com/mwydmuch/ViZDoom/blob/master/examples/python/basic.py) environment of Visual doom. The agent could play very experienced after about 1000 times of games~~

also provide the dqn training and testing code for comparision.

## reference

[Dueling Network Architectures for Deep Reinforcement Learning (arxiv)](https://arxiv.org/abs/1511.06581)