HalfCheetah

HalfCheetah is a benchmark environment used in reinforcement learning that simulates a two-dimensional half-cheetah robot, primarily to evaluate the performance of algorithms in learning effective control policies.

Papers using HalfCheetah (7)

Online Adaptive Reinforcement Learning with Echo State Networks for Non-Stationary Dynamics2026Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments2025Zero-Shot Policy Transfer in Reinforcement Learning using Buckingham's Pi Theorem2025An Advantage-based Optimization Method for Reinforcement Learning in Large Action Space2024 · 1 cites'Explaining RL Decisions with Trajectories': A Reproducibility Study2024Diagnosing Non-Markovian Observations in Reinforcement Learning via Prediction-Based Violation Scoring2026Advantage-Guided Diffusion for Model-Based Reinforcement Learning2026