HalfCheetah

HalfCheetah is a high-dimensional simulated environment used to evaluate the effectiveness of reinforcement learning policies in adapting to new system contexts without retraining.

Papers using HalfCheetah (2)

Visualizing Latent Phase Structures in Locomotion Policies: A Multi-Environment Study with Temporal Feature Extension2026Zero-shot Policy Transfer In Reinforcement Learning Using Buckingham's Pi Theorem2025