ResearchBenchmarkshuman-robot task planning and allocation on HRTPA H2,R3 (test)Follow1,163.8MakespanDQN1,158.89841,191.98421,225.071,258.1558Apr 14, 2026Evaluation ResultsMethodMethodLinksMakespanOverworkDQN2026.041,163.80PPO-Lag2026.041,170.620PF-CD3Q2026.041,172.80D3QN2026.041,174.562PF-DQN2026.041,194.260PF-PPO2026.041,275.720PF-PPO-Lag2026.041,286.160PPO2026.041,286.340