experiment: E5_qd_vs_greedy
seed: 20260704
n_replicates: 100
generations: 400

# Quality-diversity vs greedy selection (blueprint 2.5-E5). Modest grounding gives a true
# stationary state (so items can be re-introduced); selection then shapes it. Greedy
# (directional, fitness-proportional) drives toward the fittest items -> low H; qd (adds a
# novelty bonus w_i ∝ f_i·p_i^{-alpha}) resists fixation -> higher stationary H. Sweep the
# novelty exponent alpha. Prediction: qd holds higher stationary H (and tail survival)
# than greedy at matched grounding.
truth:
  K: 500
  R: 1
  tail: zipf
  zipf_s: 1.1
  tail_frac: 0.5
  tail_threshold: 1.0e-3
  init: truth

dynamics:
  n: 200
  teachers: {K_T: 1, rho: 0.0, q: 1.0}
  grounding: {m: 10, policy: proportional}   # g ~ 0.048, same for all arms
  selection: {mode: none, novelty_alpha: 0.0}
  remint: {enabled: false, period: null, H_gate: null}

metrics:
  kl_floor: 1.0e-9
  support_eps: 1.0e-9

sweep:
  - param: dynamics.selection.mode
    values: [none, greedy, qd]
  - param: dynamics.selection.novelty_alpha
    values: [0.5, 1.0, 2.0]

output:
  dir: results/figS12_quality_diversity