humphreymunn / GCR-PPOView on GitHub
GCR-PPO is a modification of PPO for multi-objective robot RL that: - uses a multi-head critic to obtain per-reward advantages and gradients, - applies priority-aware gradient surgery (PCGrad-style projection) to protect task objectives from regularisers, - runs at massively parallel GPU scale within IsaacLab/RSL-RL.
37Feb 13, 2026Updated 5 months ago

Alternatives and similar repositories for GCR-PPO

Users that are interested in GCR-PPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?