Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A simple and easy-to-use autonomous driving environment for reinforcement learning, based on the CARLA simulator.
| Date | Stars |
|---|---|
| 2026-07-31 | 261 |
| 2026-08-02 | 261 |
| 2026-08-03 | 261 |
| 2026-08-06 | 261 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
🚀 [**New Dataset Released !**](#-download-dataset)
# EasyCarla-RL: A lightweight and beginner-friendly OpenAI Gym environment built on the CARLA simulator
## Overview
EasyCarla-RL provides a lightweight and easy-to-use Gym-compatible interface for the CARLA simulator, specifically tailored for reinforcement learning (RL) applications. It integrates essential observation components such as LiDAR scans, ego vehicle states, nearby vehicle information, and waypoints. The environment supports safety-aware learning with reward and cost signals, visualization of waypoints, and customizable parameters including traffic settings, number of vehicles, and sensor range. EasyCarla-RL is designed to help both researchers and beginners efficiently train and evaluate RL agents without heavy engineering overhead.
<div align="center">
<table>
<tr>
<td><img src="assets/part1.gif" width="100%"/></td>
<td><img src="assets/part2.gif" width="100%"/></td>
<td><img src="assets/part3.gif" width="100%"/></td>
</tr>
</table>
</div>
## Installation
Clone the repository:
```bash
git clone https://github.com/silverwingsbot/EasyCarla-RL.git
cd EasyCarla-RL
```
Install the required dependencies:
```bash
pip install -r requirements.txt
```
Install EasyCarla-RL as a local Python package:
```bash
pip install -e .
```
Make sure you have a running [CARLA simulator](https://carla.org/) server compatible with your environment.
For detailed installation instructions, please refer to the [official CARLA docs](https://carla.readthedocs.io/en/0.9.13/start_quickstart/)
## Quick Start
Run a simple demo to interact with the environment:
```bash
python easycarla_demo.py
```
This script demonstrates how to:
- Create and reset the environment
- Select random or autopilot actions
- Step through the environment and receive observations, rewards, costs, and done signals
Make sure your CARLA server is running before executing the demo.
## Advanced Example: Evaluation with Diffusion Q-Learning
For a more advanced usage, you can run a pre-trained [Diffusion Q-Learning](https://github.com/Zhendong-Wang/Diffusion-Policies-for-Offline-RL) agent in the EasyCarla-RL environment:
```bash
cd example
python run_dql_in_carla.py
```
Make sure you have downloaded or prepared a trained model checkpoint under the `example/params_dql/` directory.
This example demonstrates:
- Loading a pre-trained RL agent
- Interacting with EasyCarla-RL for evaluation
- Evaluating the performance of a real RL model on a simulated autonomous driving task
## 📥 Download Dataset
This repository provides an offline dataset for training and evaluating RL agents in the EasyCarla-RL environment.
This dataset includes over **7,000 trajectories** and **1.1 million timesteps**, collected from a mix of expert and random policies (with an **8:2 ratio** of expert to random), recorded in the Town03 map. The data is stored in **HDF5 format**.
You can download it from either of the following sources:
* [Download from Hugging Face (direct link)](https://huggingface.co/datasets/silverwingsbot/easycarla/resolve/main/easycarla_offline_dataset.hdf5)
* [Download from 百度网盘 (提取码: 2049)](https://pan.baidu.com/s/1yhCFzl4RFHzxfszebYnOIg?pwd=2049)
Filename: `easycarla_offline_dataset.hdf5` Size: \~2.76 GB Format: HDF5
### Dataset Structure (HDF5)
Each sample in the dataset includes the following fields:
```
/ (root)
├── observations → shape: [N, 307] # concatenated: ego_state + lane_info + lidar + nearby_vehicles + waypoints
├── actions → shape: [N, 3] # [throttle, steer, brake]
├── rewards → shape: [N] # scalar reward per step
├── costs → shape: [N] # safety-related cost signal per step
├── done → shape: [N] # 1 if episode ends
├── next_observations → shape: [N, 307] # next-step observations, same format as observations
├── info Excerpt of 8,562 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b461b3746ad2224f, topic:reinforcement-learning, topic:rl, desc:reinforcement learning
matched fp:b461b3746ad2224f, topic:autonomous-driving, desc:autonomous driving, readme:autonomous driving