Neuroevolution-Bots is a personal project that demonstrates neuroevolution in a browser environment using TensorFlow.js, Neataptic (for neural nets) and HTML5 Canvas (for graphics). I tried to create a scaled down 2D version of the popular Gym’s Humanoid-v2 environment using Planck.js, a JavaScript rewrite of Box2D.
The bots in the simulation have simple brains (neural nets) that control their movements. Input to the brains: bot’s head position in the world space and angles of bot’s leg and knee joints; output of the brains: rotation forces to bot’s leg and knee joints. After every iteration, a fitness function chooses the most fit bots to the next iteration (fitness score of bot: how much the bot traveled to the right + whether bot fell down or not).
Two variations of neuroevolution are available:
Source code available: here
| Algorithm: | |
| Training: | |
| Goal: | walk to the right side of the screen while not falling down |
| Generation: | 1 |
| Generation Period: | 5 seconds |
| Population size: | 0 |
| Muttion Rate: | 5% |
| Avg Score: | 0 |
| Max Score: | 0 |
*live training is happening in your browser. Try dragging one of the bots
References and inspirations: