# Reference: REINVENT 4 staged-learning schema; validate with installed release
# Minimal built-in scoring example. Add model-backed endpoints only by copying
# the matching release's documented component parameters.
# Batch size, DAP settings, learning rate, and stage limits below are repository
# starting defaults; tune them from learning curves, diversity, and oracle cost.

run_type = "staged_learning"
device = "cuda:0"

[parameters]
prior_file = "priors/reinvent.prior"
agent_file = "priors/reinvent.prior"
batch_size = 64
unique_sequences = true
randomize_smiles = true
summary_csv_prefix = "outputs/reinvent"
use_checkpoint = false
purge_memories = false

[learning_strategy]
type = "dap"
sigma = 128
rate = 0.0001

[[stage]]
chkpt_file = "checkpoints/stage1.chkpt"
termination = "simple"
max_score = 1.0
min_steps = 25
max_steps = 500

[stage.scoring]
type = "geometric_mean"

[[stage.scoring.component]]
[stage.scoring.component.QED]

[[stage.scoring.component.QED.endpoint]]
name = "QED"
weight = 1