ResearchBenchmarksHuman-Robot Task Planning and Allocation on HRTPA Mean across all test scenariosFollow1,281.86MakespanD3QN1,278.71881,299.92191,321.1251,342.3281Apr 14, 2026Evaluation ResultsMethodMethodLinksMakespanOverworkD3QN2026.041,281.8625.8PF-CD3Q2026.041,300.241.1DQN2026.041,316.4722.2PF-PPO2026.041,324.210PF-PPO-Lag2026.041,324.870PPO-Lag2026.041,329.0226.7PF-DQN2026.041,332.870.2PPO2026.041,360.3918.9