ml-agents
carla
Our great sponsors
ml-agents | carla | |
---|---|---|
60 | 22 | |
16,194 | 10,347 | |
1.5% | 2.1% | |
8.1 | 8.3 | |
7 days ago | 3 days ago | |
C# | C++ | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ml-agents
-
At least I put effort into the AI prompt to generate some code that people can refer to, whereas you do absolutely nothing to contribute to the community.
and PR content: https://github.com/Unity-Technologies/ml-agents/commit/ed212103e451449bf84711a4a8f7bf11dfb1211a
-
TransformerXL + PPO Baseline + MemoryGym
Thanks! It really depends on the task that you want to implement. But in general, sticking to the standard gymnasium API is important. If you want to implement a 2D environment then PyGame is promising. If it's more like a game, check out Unity ML-Agents or Godot RL Agents. Anything simpler can also be just pure python code. You also need to carefully design your observation space, action space and reward function. My advice is to explore design choices of related environments.
-
Impact of using sockets to communicate between Python and RL environment
When looking into implementing RL in a game environment, I found that both Unity MLAgents and the third-party UnrealCV communicate between the game environments and Python using sockets. I am looking into implementing RL for Unreal and wondering about the performance impact of using sockets vs using RL C++ libraries to keep everything "in-engine"/native.
-
After 8 Hours, my ML Agents learned how to work together!
For the last question, I suggest downloading this example package and taking a look at the Soccer example. It shows how to have 2 completely different Agents on different teams learn from each other.
What helped me the most to get started was this youtube video, and then after that I would recommend going through the official unity github examples and their scenes to understand how they approached different tasks.
-
I'm failing to download a repository correctly
# Install steps - download the `ml-agents` repository `git clone https://github.com/Unity-Technologies/ml-agents` - create a Python folder in `ml-agents` and clone `social_rl` repo into it `svn export https://github.com/google-research/google-research/trunk/social_rl` - copy `environments.py` and `gymwrappers.py` into this Python folder - create a python3.8 environment and install `social_rl` requirements `conda create -n mlagents python=3.8` `pip install -r requirements.txt` - install `ml-agents_envs`, `ml-agents` and `gym-unity` from the `ml-agents` repository `python install setup.py`
-
8+ Reinforcement Learning Project Ideas
Unity ML-Agents is a relatively new add-on to the Unity game engine. It allows game developers to train intelligent NPCs for games and enables researchers to create graphics- and physics-rich RL environments. Project ideas to explore include:
-
How to train agents to play volleyball using deep reinforcement learning
Descriptions of the configurations are available in the ML-Agents official documentation.
-
🏐 Ultimate Volleyball: A 3D Volleyball environment built using Unity ML-Agents
Inspired by Slime Volleyball Gym, I built a 3D Volleyball environment using Unity's ML-Agents toolkit. The full project is open-source and available at: 🏐 Ultimate Volleyball.
carla
- What good Autonomous Driving simulators for research?
-
Importing map from google maps
If you are looking for a different simulator, I would suggest using (Carla)[https://carla.org/] with ROS bridge and it also has an inbuilt support for OSM which worked flawlessly (you have to install it from source to get the OSM plugin).
-
[D] Doing my (bachelor) thesis on RL. Which topic do you like best?
(3) I would suggest you use CARLA or TORCS for self-driving cars in RL as they are common test beds.
-
Currently writing out a plan for an RL based path-planning project. (I'm doing it for my Smart Vehicles course in my Master's Degree) Don't have much domain knowledge atm but looking for some advice on how to approach the problem?
Carla: https://github.com/carla-simulator/carla
-
8+ Reinforcement Learning Project Ideas
CARLA
- [R] CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
-
Is it possible to train a self driving car on google colab?
I've been trying for a while now and I started thinking it may not be possible. If anyone has managed to train a self-driving car simulator using openai gym on google colab(preferably), or on any remote server (AWS, GCP, ...) please let me know. So far, I tried carla, airsim, svl, deepdrive and they are all equally useless unless run locally with a gui. I'd really appreciate if someone suggests some way that actually can make it possible.
-
What is the best source to learn how to build a self-driving car from scratch?
If you're more on the simulation side, you can do it with CARLA: http://carla.org/ You can add almost any sensor type there, create your pipeline, even use Openpilot from Comma ai.
-
Made a selfDrivingCar recently.
Great work! For more data acquisition (perhaps will help the domain gap) you can look into CARLA: https://carla.org
What are some alternatives?
AirSim - Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
simulator - A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
openpilot - openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for 250+ supported car makes and models.
apollo - An open autonomous driving platform
webots - Webots Robot Simulator
gym - A toolkit for developing and comparing reinforcement learning algorithms.
deepdrive - Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving
apollo - 🚀 Apollo/GraphQL integration for VueJS
pwnagotchi - (⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
gym-donkeycar - OpenAI gym environment for donkeycar simulator