NERO 1.0 video (2005)

Training: Learn to approach the enemy.
In this learning scenario, the agents start out with empty brains. In the slider control panel in the lower right of the screen, the player assigns the agents the task of approaching the enemy. In a relatively short amount of time, the agents learn to approach the enemy on their own, without explicit code telling them how to accomplish that goal.
Click "Play" below or download a high resolution version

Training switch: Learn to approach the enemy, then learn to avoid the enemy.
In this scenario, the robots have already been trained to approach and attack the enemy. The player then inhabits the enemy in first person mode and begins fighting back. The robots respond by gradually approaching the player in fewer and fewer numbers.
Click "Play" below or download a high resolution version

Battle between simple aggressive team and simple avoiding team.
NERO battle scenarios do not involve active learning. Instead, the teams of agents have been trained previously and bring their trained behavior to the battlefield. This battle involves teams that have been trained in a straightforward way to either approach the enemy or avoid the enemy.
Click "Play" below or download a high resolution version

Battle between more complex teams
In this battle scenario, the two teams were trained using more sophisticated strategies which produce more complex behavior in battle. The cooperative behavior evident in the blue team is not the result of scripting or an explicit cooperative output in the agents' networks. It is emergent behavior.
Click "Play" below or download a high resolution version

Note: The local copies of the following two highly compressed movies require downloading and installing the DivX codec so that they can run on your system.

Download DivX here.

Battle between sophisticated teams
These teams learned on their own to cluster together in groups and keep a safe distance, as well as pivot in and out of range. They display an effective and sophisticated battlefield strategy. As with all NERO movies, this behavior was discovered by evolution and not scripted.
Click "Play" below or download a high resolution version

Complex Maze Dispersion Demo
The robots in this video were asked to weave their way through a complicated maze to get to a flag at the other end. In addition, the "reward dispersion" slider was set to high, meaning that they received more fitness if they did not all take the same route. Computationally, this is a very difficult problem to solve: path-finding plus staying away from other at the same time. However, rtNEAT (the technology behind NERO) was able to evolve such a capability on its own with no path-panning algorithms built into the system!
Click "Play" below or download a high resolution version

NERO beta video (2004)

Training

Note: In training, the trainees are blue and the enemy is red. Red smoke is from enemy shots, blue is from the learners.

Training Mode: Learning to approach an enemy.
The NERO robots begin the clip with empty brains and wandering aimlessly. Over a couple minutes, they learn to approach the enemy. The learning can be seen in real-time. Notice how more and more robots exhibit the correct behavior.
Click "Play" below or download a high resolution version

Training Mode: Training to avoid an enemy (first-person view)
This clip was taken in the middle of avoidance training. The robots are learning to avoid the player, who is acting as their enemy. They can be observed running away.
Click "Play" below or download a high resolution version

Training Mode: Learning to navigate a maze.
The robots have been training inside a maze for several minutes before this clip was recorded. At this point, the robots have learned maze navigation on their own without any pathfinding algorithm
Click "Play" below or download a high resolution version

Battle

Note: In battle one team is red and the other blue. Red smoke is from red team shots, blue is from the blue team.

Battle Mode: Aggressive vs. Aggressive
Two teams that were trained to be aggressive are pitted against each other in battle. Notice they both fearlessly meet in the middle. Small chase sequences can be observed as robots break away from the main melee.
Click "Play" below or download a high resolution version

Battle Mode: Aggressive vs. Avoiding
An aggressive team takes on a team trained using avoidance training (see above clip of avoidance training). Notice how easy it is to tell which is which. The avoidant team retreats to a wall and eventually to a corner for a last stand.
Click "Play" below or download a high resolution version