https://github.com/hasnainroopawalla/deep-q-learning
Playing Atari Games (OpenAI Gym) using Deep Reinforcement Learning.
https://github.com/hasnainroopawalla/deep-q-learning
gym-environment python q-learning reinforcement-learning
Last synced: 6 months ago
JSON representation
Playing Atari Games (OpenAI Gym) using Deep Reinforcement Learning.
- Host: GitHub
- URL: https://github.com/hasnainroopawalla/deep-q-learning
- Owner: hasnainroopawalla
- License: mit
- Created: 2022-01-06T12:35:09.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2022-01-12T15:57:46.000Z (over 3 years ago)
- Last Synced: 2025-02-15T21:47:39.317Z (8 months ago)
- Topics: gym-environment, python, q-learning, reinforcement-learning
- Language: Python
- Homepage:
- Size: 438 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Deep Q-Learning (Reinforcement Learning)
This Python Package can be used to train an agent to play various Atari Games ([OpenAI Gym](https://gym.openai.com/envs/#classic_control)) using [Deep Q-Learning](https://www.tensorflow.org/agents/tutorials/0_intro_rl).
## 📝 Table of Contents
- [Getting Started](#getting_started)
- [Agents](#agents)
### Install all dependencies:
```
$ pip install -r requirements.txt
```
### Basic usage:
```
$ python -m dqn --agent --mode
```
#### Parameters
- `--agent`: Specify the agent to be used (Refer to [Agents](#agents)).
- `--mode`: Train an agent (`train`) or simulate a trained agent (`simulate`).
### CartPole-v0 (`--agent cartpole`)
More information [here](https://gym.openai.com/envs/CartPole-v0/).
The following simulation is 3 episodes of a trained _CartPole_ agent receiving a mean reward of `200.0` after training for 1000 episodes.
#### To Train:
```
$ python -m dqn --agent cartpole --mode train
```
#### To Simulate:
```
$ python -m dqn --agent cartpole --mode simulate
```
### Pong-V0 (`--agent pong`)
> In-progress