RLBot
RoboLeague
Our great sponsors
RLBot | RoboLeague | |
---|---|---|
10 | 11 | |
581 | 295 | |
0.9% | - | |
5.0 | 0.0 | |
2 months ago | about 3 years ago | |
Python | C# | |
MIT License | 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.
RLBot
- [Rocketleague] Comment jouer contre Nexto avec un ami ?
- How do I play against Nexto with my friend?
-
Nexto, a community machine learning Rocket League bot, even understands our most important rule.
You can probably find the info for the setup here: https://github.com/RLBot/RLBot/wiki/LAN-Setup
- Who finds these controls strange?
-
How do flips work?
https://github.com/RLBot/RLBot/wiki/Useful-Game-Values you'll probably find this interesting as well
-
Is there a simple way I can rewind 5 seconds back to retry and shot I missed for training?
https://github.com/RLBot/RLBot/wiki/Manipulating-Game-State Have a look at this. When you click on the python link it also tells you how to restore a snapshot, which means you only have to store the game tick packets somehow. Hope it helps! And there's always the discord in case you need more help, people might answer there more quickly.
-
An attempt to document the entire history of the modding scene
Early work creating custom bots: https://github.com/RLBot/RLBot/commit/348084e21d809b1e0dd9846513fb094b9f6ff506
- Do the Rocket League goalposts have a rounded or square collision?
- Doing a clone of Rocket League for AI experiments. Trained an agent to air dribble the ball.
RoboLeague
-
My ML AI bot just learned how to turtle (10 seconds mark) | RoboLeague car soccer environment made in Unity3D
Hello everyone! In my first devlog, I introduced you to RoboLeague - my open-source car soccer environment for AI experiments and research inspired by Rocket League. It is made in Unity3D, every Rocket League mechanic you see in the videos was implemented from scratch and is identical to the real game. I will also release a free game, where you will be able to refine your skills playing solo or vs the AI. The demo should be released soon (TM). More videos and info about the demo will be on my Twitter.
already there https://github.com/roboserg/RoboLeague
-
Trained an AI agent for over 24h to freestyle through the rings map. Made with Unity3d, more info inside.
Hello everyone! In my first devlog, I introduced you to RoboLeague - my open-source car soccer environment for AI experiments and research inspired by Rocket League. It is made in Unity3D, every Rocket League mechanic you see in the videos was implemented from scratch and is identical to the real game. I will also release a free game, where you will be able to refine your skills playing solo or vs the AI. The demo should be released soon (TM). More videos and info about the demo will be on my Twitter.
-
AI learned to freestyle in the obstacle course on its own! The power of Machine Learning.
Twitter| RoboLeague Github | Previous devlog
-
Trained an AI with ML to air dribble the ball in my Rocket League clone for AI research
The project is called RoboLeague and is open source, available here. More videos are also on my Twitter.
-
RoboLeague devlog #2: Training an AI to navigate an obstacle course with Unity ML agents
Twitter| RoboLeague Github | Previous devlog
-
P Doing A Clone Of Rocket League For Ai
The code is here https://github.com/roboserg/RoboLeague/blob/master/Assets/ML-Agents/Experiments/AirDribble/AirDribbleAgent.cs
The project is called RoboLeague and is open source, available here. More videos are also on my Twitter.
-
Doing a clone of Rocket League for AI experiments. Trained an agent to air dribble the ball.
The agent code is here - https://github.com/roboserg/RoboLeague/blob/master/Assets/ML-Agents/Experiments/AirDribble/AirDribbleAgent.cs
What are some alternatives?
RL-GARAGE-PRE-BOT - RL-GARAGE-PRE-BOT # Auto Trade Bumper, Auto Reply, Item Alerts
TotalWarSimulator - Total War Battle simulator for AI research
carball - 📈 A Rocket League replay decompiling and analysis library
VirxERLU - Big thanks to ddthj/GoslingUtils for the basis of VirxERLU. However, VirxERLU improves upon many things. This includes pathfinding, shot validation, and aerials. It also adds many things, like support for TMCP and a GUI for debugging.
ml-agents - The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
ultimate-volleyball-starter - Tutorial kit for building a 3D deep reinforcement learning environment with Unity ML-Agents.
BakkesMod-process-automation
com.openai.unity - A Non-Official OpenAI Rest Client for Unity (UPM)
BotimusPrime - Rocket League bot made with the RLBot framework
ultimate-volleyball - 3D RL Volleyball environment built on Unity ML-Agents