Implementation:Farama Foundation Gymnasium Walker2dEnv V5

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 Walker2d v5 MuJoCo locomotion environment provided by Gymnasium.

Description

The Walker2d environment builds on the Hopper environment by adding another set of legs, allowing the robot to walk forward instead of hop. The walker is a two-dimensional bipedal robot consisting of seven main body parts: a single torso at the top, two thighs, two legs below the thighs, and two feet. The goal is to walk in the forward (right) direction by applying torque to the six hinges connecting the body parts. The reward function combines a healthy reward, a forward reward based on x-velocity, and a control cost penalty. The v5 version fixes unequal foot friction values (both feet now have friction 1.9) and the healthy_reward bug.

Usage

Use this environment for benchmarking bipedal locomotion RL algorithms. It provides a moderate difficulty challenge between the simpler Hopper and the more complex Humanoid environments. The v5 version includes individual reward terms in info and z_distance_from_origin tracking.

Code Reference

Source Location

Repository: Farama_Foundation_Gymnasium
File: gymnasium/envs/mujoco/walker2d_v5.py

Signature

class Walker2dEnv(MujocoEnv, utils.EzPickle):
    def __init__(
        self,
        xml_file: str = "walker2d_v5.xml",
        frame_skip: int = 4,
        default_camera_config: dict[str, float | int] = DEFAULT_CAMERA_CONFIG,
        forward_reward_weight: float = 1.0,
        ctrl_cost_weight: float = 1e-3,
        healthy_reward: float = 1.0,
        terminate_when_unhealthy: bool = True,
        healthy_z_range: tuple[float, float] = (0.8, 2.0),
        healthy_angle_range: tuple[float, float] = (-1.0, 1.0),
        reset_noise_scale: float = 5e-3,
        exclude_current_positions_from_observation: bool = True,
        **kwargs,
    )

Import

import gymnasium as gym
env = gym.make("Walker2d-v5")

I/O Contract

Inputs

Name	Type	Required	Description
action	np.ndarray (6,)	Yes	Torques applied to thigh, leg, foot, left thigh, left leg, and left foot joints, range [-1, 1]

Outputs

Name	Type	Description
observation	np.ndarray (17,)	State vector: qpos (8 elements, x excluded), qvel (9 elements, clipped to [-10, 10])
reward	float	healthy_reward + forward_reward - ctrl_cost
terminated	bool	True if walker is unhealthy (z outside [0.8, 2.0] or angle outside [-1, 1])
truncated	bool	Episode truncation (handled by TimeLimit wrapper)
info	dict	Contains x_position, z_distance_from_origin, x_velocity, reward_forward, reward_ctrl, reward_survive

Usage Examples

import gymnasium as gym

env = gym.make("Walker2d-v5")
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