Reinforcement Learning on Supply Chain Optimization Environment (test) benchmark leaderboard · SOTA2 Research

Reinforcement Learning on Supply Chain Optimization Environment (test)

20.51Max RewardQuantum-Inspired Reinforcement Learning framework

Evaluation Results

Method
Quantum-Inspired Reinforcement Learning framework2026.01	20.51	14.85	20.51
PPO2026.01	20.2	13.95	19.61
DDQN2026.01	19.6	13.25	18.91
ACKTR2026.01	19.1	12.75	18.41
DDPG2026.01	18.7	12.35	18.01
Ensemble RL (Bootstrapped DQN)2026.01	18.2	11.85	17.51
ACER2026.01	17.8	11.25	16.91
Human (reference)2026.01	13.1	13.1	13.1
GRAPE2026.01	13	13	13
MPC2026.01	12.2	12.2	12.2