# Hopper-v1

Make a two-dimensional one-legged robot hop forward as fast as possible.

Hopper-v1 defines "solving" as getting average reward of 3800.0 over 100 consecutive trials.

The robot model is based on work by Erez, Tassa, and Todorov [Erez11].

Make a two-dimensional one-legged robot hop forward as fast as possible.

Hopper-v1 defines "solving" as getting average reward of 3800.0 over 100 consecutive trials.

The robot model is based on work by Erez, Tassa, and Todorov [Erez11].

[Erez11] | T Erez, Y Tassa, E Todorov, "Infinite Horizon Model Predictive Control for Nonlinear Periodic Tasks", 2011. |