Implementation:Farama Foundation Gymnasium HumanoidStandupEnv V4
| Knowledge Sources | |
|---|---|
| Domains | Reinforcement_Learning, MuJoCo_Environments |
| Last Updated | 2026-02-15 03:00 GMT |
Overview
Concrete implementation of the HumanoidStandup v4 MuJoCo environment provided by Gymnasium.
Description
The HumanoidStandup v4 environment uses the same 3D bipedal humanoid robot as the Humanoid environment, but the robot starts laying on the ground. The goal is to make the humanoid stand up and keep it standing. The reward is: uph_cost - quad_ctrl_cost - quad_impact_cost + 1, where uph_cost is the z-position divided by the timestep, quad_ctrl_cost is 0.1 times the squared control, and quad_impact_cost is 0.5e-6 times the squared contact forces (clamped to max 10). The environment never terminates; episodes end only through truncation. The observation space is 376-dimensional, including qpos, qvel, cinert, cvel, qfrc_actuator, and cfrc_ext. This is a minimal v4 implementation with hardcoded reward weights.
Usage
Use this environment for reproducing results from papers that used HumanoidStandup-v4. For new research, consider HumanoidStandup-v5 which provides configurable reward weights, excludes constant-zero observations, and offers more detailed info dictionaries.
Code Reference
Source Location
- Repository: Farama_Foundation_Gymnasium
- File: gymnasium/envs/mujoco/humanoidstandup_v4.py
Signature
class HumanoidStandupEnv(MujocoEnv, utils.EzPickle):
def __init__(self, **kwargs)
Import
import gymnasium as gym
env = gym.make("HumanoidStandup-v4")
I/O Contract
Inputs
| Name | Type | Required | Description |
|---|---|---|---|
| action | np.ndarray (17,) | Yes | Torques applied to the 17 hinge joints, range [-0.4, 0.4] |
Outputs
| Name | Type | Description |
|---|---|---|
| observation | np.ndarray (376,) | State vector: qpos (22, x/y excluded), qvel (23), cinert, cvel, qfrc_actuator, cfrc_ext (includes worldbody) |
| reward | float | uph_cost - quad_ctrl_cost - quad_impact_cost + 1 |
| terminated | bool | Always False (HumanoidStandup never terminates) |
| truncated | bool | Episode truncation (handled by TimeLimit wrapper, default 1000 timesteps) |
| info | dict | Contains reward_linup, reward_quadctrl, reward_impact |
Usage Examples
import gymnasium as gym
env = gym.make("HumanoidStandup-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()