Meet Rezzy

A NEAT-based ML agent trained through curriculum learning.
Demonstrating the power of neuroevolution in the Resonance Engine.

Meet Rezzy: The ML Agent

NEAT neuroevolution agent trained through curriculum learning

NEAT

NEAT Neuroevolution

Pure Rust implementation of NeuroEvolution of Augmenting Topologies. Evolves neural network topology and weights simultaneously.

Observation

Observation Space

10-dimensional normalized state vectors: player position, velocity, goal location, hazard detection, and wall proximity.

Actions

Action Space

6 discrete actions: noop, move left, move right, jump, move left + jump, move right + jump.

Curriculum

Curriculum Learning

Progressive difficulty: L1 (Move Right) → L2 (Jump to Goal) → L3 (Avoid Enemy) → L4 (Platform Climb) → L5 (Gauntlet).

Training Results

100% success on training levels; generalization to novel variants in progress

L1
Move Right - 100% ✓
L2
Jump to Goal - 100%
L3
Avoid Enemy - 100%
L4
Platform Climb - 100%
L5
Gauntlet - 100%
Level Training Generalization Status
L1: Move Right 100% 100% ✓ Complete
L2: Jump to Goal 100% 35% In Progress
L3: Avoid Enemy 100% 45% In Progress
L4: Platform Climb 100% TBD In Progress
L5: Gauntlet 100% TBD In Progress

Training Rezzy

NEAT neuroevolution with curriculum learning

# Clone the repository (when available)
# cd resonance-agent

# Train Rezzy on platformer challenges
cargo run --release --bin train_platformer

# Test a trained model
cargo run --release --bin test_model -- --model models/level5_gauntlet.json

# View training results
cargo run --release --bin view_stats

Learn More About Ludo Resonance

Explore the engine and NAL that power Rezzy's learning capabilities.

Explore the Engine Learn About NAL Back to Home