vendsim-vb2 / vendsim_vb2 /rewards.py
retroam
Add VendSim VB2 environment
00b2ea2
raw
history blame contribute delete
257 Bytes
from __future__ import annotations
def compute_reward(
final_bank_balance: float, dense_components: list[float], use_dense: bool
) -> float:
if not use_dense:
return final_bank_balance
return final_bank_balance + sum(dense_components)