List your company

Action-component payoff optimization on HybridCoop+AllD (off-diagonal)

2.05Per-interaction PayoffTD3
1.7381.8191.91.981May 8, 2026

Evaluation results

MethodLinks
TD3Touter=15, Seeds=32026.052.05
DDPGTouter=15, Seeds=32026.052.04
DPGTouter=15, Seeds=32026.051.98
DPGTouter=15, Seeds=32026.051.85
TD3Touter=15, Seeds=32026.051.83
DDPGTouter=15, Seeds=32026.051.75