Hopper

The 'Hopper' dataset/benchmark is used to evaluate model-based reinforcement learning algorithms by providing a simulated environment where agents learn to control a bipedal hopper robot.

Papers using Hopper (3)

Stabilized neural Hamilton--Jacobi--Bellman solvers: Error analysis and applications in model-based reinforcement learning2026Advantage-Guided Diffusion for Model-Based Reinforcement Learning2026Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement Learning2026