AMaze: fully discrete training with three regimes (direct, scaffolding, interactive) and two algorithms (A2C, PPO)

<p>Dataset containing all training artifacts (final models, training curves, intermediate visualizations, ...) as well as the raw data used to assert generalization capabilities.</p> <p>The associated archive final_behavior.tar.gz provides a visualization of every replicate's final behavior for easier navigation.</p> <p>Distribution files contain a sampling across 1000 seeds, 5 probabilities for traps and lures, 4 sizes and 5 set sizes resulting in 486356 mazes. Descriptive graphs provide an overview of the accessible "maze space".</p> <p>&nbsp;</p> <p>v2: Added script to aggregate run dynamics (mean reward, errors, maze lengths...) and resulting generated dataset (csv) and plots (pdf)</p>