Implementation:Farama Foundation Gymnasium HalfCheetahEnv V4

Knowledge Sources	Farama_Foundation_Gymnasium Gymnasium Docs
Domains	Reinforcement_Learning, MuJoCo_Environments
Last Updated	2026-02-15 03:00 GMT

Overview

Concrete implementation of the HalfCheetah v4 MuJoCo locomotion environment provided by Gymnasium.

Description

The HalfCheetah v4 environment is a 2-dimensional robot consisting of 9 body parts and 8 joints. The goal is to apply torque to the joints to make the cheetah run forward as fast as possible. The cheetah's torso and head are fixed, and torque can only be applied to 6 joints: the front and back thighs, shins, and feet. The reward is forward_reward - ctrl_cost. The HalfCheetah never terminates; episodes only end through truncation. This is the legacy version using MuJoCo bindings (mujoco >= 2.1.3).

Usage

Use this environment for reproducing results from papers that used HalfCheetah-v4. For new projects, consider HalfCheetah-v5 which adds more configuration options and consistent reward naming. The HalfCheetah is one of the most commonly used MuJoCo benchmarks for RL algorithm evaluation.

Code Reference

Source Location

Repository: Farama_Foundation_Gymnasium
File: gymnasium/envs/mujoco/half_cheetah_v4.py

Signature

class HalfCheetahEnv(MujocoEnv, utils.EzPickle):
    def __init__(
        self,
        forward_reward_weight=1.0,
        ctrl_cost_weight=0.1,
        reset_noise_scale=0.1,
        exclude_current_positions_from_observation=True,
        **kwargs,
    )

Import

import gymnasium as gym
env = gym.make("HalfCheetah-v4")

I/O Contract

Inputs

Name	Type	Required	Description
action	np.ndarray (6,)	Yes	Torques applied to back thigh, back shin, back foot, front thigh, front shin, front foot, range [-1, 1]

Outputs

Name	Type	Description
observation	np.ndarray (17,)	State vector: qpos (8 elements, x excluded by default), qvel (9 elements)
reward	float	forward_reward - ctrl_cost
terminated	bool	Always False (HalfCheetah never terminates)
truncated	bool	Episode truncation (handled by TimeLimit wrapper)
info	dict	Contains x_position, x_velocity, reward_run, reward_ctrl

Usage Examples

import gymnasium as gym

env = gym.make("HalfCheetah-v4")
observation, info = env.reset(seed=42)

for _ in range(1000):
    action = env.action_space.sample()
    observation, reward, terminated, truncated, info = env.step(action)
    if terminated or truncated:
        observation, info = env.reset()

env.close()

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment