swimmer_minimal.py

import gymnasium as gym
import numpy as np
from gymnasium.envs.mujoco.mujoco_env import MujocoEnv

# Env initialization
env = gym.make("Swimmer-v4", render_mode="human")
# Wrap to have reward statistics
env = gym.wrappers.RecordEpisodeStatistics(env)
mujoco_env = env.unwrapped
n_joints = 2
assert isinstance(mujoco_env, MujocoEnv)
# PD Controller gains
kp, kd = 10, 0.5
# Reset the environment
t, _ = 0.0, env.reset(seed=0)
# Oscillators parameters
omega = 2 * np.pi * 0.62 * np.ones(n_joints)
phase = 2 * np.pi * np.array([0.00, 0.95])

while True:
    env.render()
    # Open-Loop Control using oscillators
    desired_qpos = np.sin(omega * t + phase)
    # PD Control: convert to torque, desired qvel is zero
    desired_torques = (
        kp * (desired_qpos - mujoco_env.data.qpos[-n_joints:])
        - kd * mujoco_env.data.qvel[-n_joints:]
    )
    desired_torques = np.clip(desired_torques, -1.0, 1.0)  # clip to action bounds
    _, reward, terminated, truncated, info = env.step(desired_torques)
    t += mujoco_env.dt

    if terminated or truncated:
        print(f"Episode return: {float(info['episode']['r'].item()):.2f}")
        t, _ = 0.0, env.reset()

Paper: https://arxiv.org/abs/2310.05808