ResearchBenchmarkshuman-robot task planning and allocation on HRTPA H2,R1 (test)Follow1,161.74MakespanPF-DQN1,152.16721,216.78361,281.41,346.0164Apr 14, 2026Evaluation ResultsMethodMethodLinksMakespanOverworkPF-DQN2026.041,161.742D3QN2026.041,193.520PF-PPO2026.041,215.740PPO2026.041,217.7416PF-PPO-Lag2026.041,222.220DQN2026.041,240.214PF-CD3Q2026.041,293.2810PPO-Lag2026.041,401.060