This project explores the application of reinforcement learning (RL) to train humanoid robots for dynamic rock climbing movements, focusing on achieving the challenging "dyno" maneuver. Using the Proximal Policy Optimization (PPO) algorithm, the simulation integrates physics-based environments to model realistic climbing scenarios.
These files are s1ddh-rth/HumanoidClimb-RL's own configuration. They tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
CLAUDE.md A 3,185 tok