A car soccer environment inspired by Rocket League for deep reinforcement learning experiments in an adversarial self-play setting.
-
Updated
Feb 8, 2021 - C#
A car soccer environment inspired by Rocket League for deep reinforcement learning experiments in an adversarial self-play setting.
Make autonomous landing rockets using Deep Reinforcement Learning (Unity ML-Agents)
Unity로 멀티 에이전트 강화학습(MARL) 수행하기 위한 프레임 워크 제공
Nowadays Using machine learning methods at simulations systems has been gaining importance with spreading and growing machine learning methods. The main purpose of using simulations get a big gain because of can cause of lots of material and spiritual damages. Simulations can use in the military sector as can use in too diverse areas. developing…
Training a car to drive within the lanes in a Unity driving environment
🤖 Creation of an RL environment with Unity, where an agent must learn to survive by moving 🦿 and shooting🔫, using ML-Agents !
🧩 Create your own puzzle, use my agents to solve it 🤖 try them out! 🧩
Training an AI for Total Wipeout using Unity MLAgents
Autonomous Racing Car Learning Environment using Unity and ML-Agents.
MLAgents Unity project for Training and tweaking simple Tank agents
Pacman AI implementation, credit to Volkan IlBeyli for the PacMan clone base->
A Self Driving Car, written in the Unity game engine, that uses deep reinforcement learning, ray casting and imitation learning to drive around a track on its own.
A project created with ML-Agents for AIs that play table tennis.
Most important scripts from my final degree project using MLAgents (Deep Reinforcement Learning) and Unity. It also includes a traditional AI algorithm to be compared with the ML one. Both AIs (ML and heuristic) had very similar results in a bird race, both AI methods are valid for this type of game.
ML-Agents Training Environments for Reinforcement Learning
This is a ML Unity project that works with ML agents RL to train a flying-trigger enemy NPC.
Reinforcement learning approach to physics based car which learns to avoid obstacles. Project was made in Unity, using MLAgents, reinfercement learning and C# scripts. The car recieves positive reward for driving into the goal and negative reward for driving into the walls, obstacles or for circling around.
Add a description, image, and links to the mlagents topic page so that developers can more easily learn about it.
To associate your repository with the mlagents topic, visit your repo's landing page and select "manage topics."