ResearchBenchmarkshuman-robot task planning and allocation on HRTPA H1,R1 (test)Follow1,594.96MakespanPF-PPO1,588.07441,634.55221,681.031,727.5078Apr 14, 2026Evaluation ResultsMethodMethodLinksMakespanOverworkPF-PPO2026.041,594.960PF-PPO-Lag2026.041,598.560PPO2026.041,615.760.46D3QN2026.041,635.940.56PF-CD3Q2026.041,638.960PPO-Lag2026.041,656.240.56DQN2026.041,764.60.56PF-DQN2026.041,767.10