ResearchBenchmarkshuman-robot task planning and allocation on HRTPA H3,R2 (test)Follow1,113.86MakespanPF-DQN1,112.6641,120.7371,128.811,136.883Apr 14, 2026Evaluation ResultsMethodMethodLinksMakespanOverworkPF-DQN2026.041,113.860PPO-Lag2026.041,118.380DQN2026.041,121.180PF-PPO2026.041,128.280D3QN2026.041,129.10PF-CD3Q2026.041,130.50PF-PPO-Lag2026.041,136.860PPO2026.041,143.760