View PDF HTML (experimental)

Abstract:Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy. A natural design choice is whether to use a single (unified) critic that estimates the combined value of all objectives, or separate (dual) critics with disjoint reward signals. We compare the two on the Unitree G1 humanoid (23 active DoF, of which 17 are policy-controlled) in NVIDIA Isaac Lab, training loco-manipulation policies through sequential curricula that progress from stationary reaching to walking with variable-orientation targets. Under a matched compute budget, the dual-critic run reaches targets 3.5x faster (6.5 vs. 22.6 simulation steps), achieves 2x higher throughput (14.3 vs. 7.0 validated reaches per 1,000 steps), and attains a higher validated reach rate (65.2% vs. 53.8%) than the unified-critic run in a standardized evaluation. Adding five anti-gaming reward mechanisms on top of the dual critic yields no further improvement (60.9% vs. 65.2%). We report this as an efficiency gap between two trained policies rather than an isolated effect of the critic: the two runs also differ in curriculum schedule, arm action dimensionality and one locomotion reward weight, and each is a single seed. The results are nonetheless suggestive for the emerging paradigm of RL fine-tuning of imitation-learned policies, where a unified critic may suppress pre-trained arm behavior through competing locomotion gradients. We argue that critic architecture deserves explicit treatment as a design variable in multi-objective humanoid RL, and specify the single-variable ablation required to establish its causal contribution. Code, trained checkpoints and a project page are available at this https URL

Submission history

From: Mehmet Turan Yardımcı [view email]
[v1] Wed, 10 Jun 2026 10:21:38 UTC (486 KB)
[v2] Thu, 30 Jul 2026 17:56:02 UTC (499 KB)