DangerDano . 7/20/24 DangerDano . 7/20/24

Egg-Bot Triumphs!

Check out how the Egg-Bot performed overnight and see the impact of splitting tasks into separate neural networks.

DangerDano . 7/19/24 DangerDano . 7/19/24

Hello Egg-Bot!

Building and training the Egg Bot, a new ML-Agent with separate neural networks for movement and turret control, in a zombie apocalypse scenario.

DangerDano . 7/13/24 DangerDano . 7/13/24

Evaluating the results of training the agents with obstacles as a new challenge.

DangerDano . 7/12/24 DangerDano . 7/12/24

After our first night of training, it’s time to evaluate the results of our goal-seeking agent.

DangerDano . 7/11/24 DangerDano . 7/11/24

Training our agents on our procedurally generated platform using Proximal Policy Optimization (PPO).

DangerDano . 7/10/24 DangerDano . 7/10/24

A look into how we build our ML-Agents to learn in our procedurally generated environments.

DangerDano . 7/9/24 DangerDano . 7/9/24

A Procedurally Generated Platform using a Hexagonal Grid Designed to Introduce Progressive Challenges for our Agents as They Progress.

DangerDano . 5/28/19 DangerDano . 5/28/19

Easily Build ML-Agents with Modular Design in Unity