Limb-as-agent MAPPO with a shared global critic speeds up humanoid walking policy training and improves gait smoothness over single-agent PPO in simulation and on hardware.
Biped dynamic walking using reinforcement learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion
Limb-as-agent MAPPO with a shared global critic speeds up humanoid walking policy training and improves gait smoothness over single-agent PPO in simulation and on hardware.