All Projects → dilmerv → UnityMLEssentials

dilmerv / UnityMLEssentials

Licence: other
Various examples of ml-agents while teaching concepts about it in YouTube

Programming Languages

C#
18002 projects
ShaderLab
938 projects
HLSL
714 projects

Projects that are alternatives of or similar to UnityMLEssentials

ActiveRagdollControllers
Research into controllers for 2d and 3d Active Ragdolls (using MujocoUnity+ml_agents)
Stars: ✭ 30 (-68.09%)
Mutual labels:  ml-agents
DQN-using-PyTorch-and-ML-Agents
A simple example of how to implement vector based DQN using PyTorch and a ML-Agents environment
Stars: ✭ 81 (-13.83%)
Mutual labels:  ml-agents
Deep Reinforcement Learning
Repo for the Deep Reinforcement Learning Nanodegree program
Stars: ✭ 4,012 (+4168.09%)
Mutual labels:  ml-agents
ML-Agents-with-Google-Colab
Train reinforcement learning agent using ML-Agents with Google Colab.
Stars: ✭ 27 (-71.28%)
Mutual labels:  ml-agents

UnityMLEssentials

Various examples of ml-agents while teaching concepts about it in my YouTube Channel

Example Scenes: (New Demos In Progress)

ParkingLot.unity Demonstrates how to park a car with machine learning. ParkingLotAdvanced.unity Demonstrates how to park a car with machine learning in a more advanced area.

Config used -> /Assets/Config/SelfParking.yaml

CrossTheRoad.unity Demonstrates how to mimic Crossy Road game mechanic with machine learning.

CrossTheRoad.unity Demonstrates how to mimic Crossy Road game mechanic with machine learning.

Config used -> /Assets/Config/CrossTheRoad.yaml

BasicPathFinding.unity Demonstrates how agents learn to reach a goal and walk through an area.

Config used -> /Assets/Config/PlayerMaze.yaml

BasicAvoidance.unity Demonstrates how agents learn to avoid objects coming towards them.

Config used -> /Assets/Config/PlayerAvoidance.yaml

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].