SOURCE-LINKED INTELLIGENCE

Where Entropy Is Measured Matters: Policy Geometry in Bounded Continuous-Control PPO

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Many continuous-control policies are optimized as unbounded Gaussians and then mapped into bounded actions. We show that where entropy is measured changes the policy geometry learned by proximal policy optimization (PPO). In an 80-muscle MyoLeg task, a clipped Gaussian executes 89.07% of actions within 5% of a bound. A same-state decomposition shows that this is not due to variance alone: setting variance to zero still leaves 83.83% of actions near a bound, while 82.12% of state-conditioned means lie outside the executable interval. Replacing clipping with a tanh map does not remove the high-v

Read original source ↗ Open in workspace

recordType

paper

region

Global