强化学习基础

import gymnasium as gym

# To see all environments you can create
gym.pprint_registry()

# Run `pip install "gymnasium[classic-control]"` for this example.
import gymnasium as gym
from gymnasium.utils.save_video import save_video


# Create our training environment - a cart with a pole that needs balancing
# "render_mode" parameter that specifies how the environment should be visualized.
# See Env.render() for details on different render modes.
# The render mode determines whether you see a visual window (“human”),
# get image arrays (“rgb_array”), or run without visuals (None - fastest for training).
env = gym.make("CartPole-v1", render_mode="rgb_array_list")

# Reset environment to start a new episode
# For initializing the environment with a particular random seed or options (see the
# environment documentation for possible values) use the seed or options parameters with reset().
observation, info = env.reset()
# observation: what the agent can "see" - cart position, velocity, pole angle, etc.
# info: extra debugging information (usually not needed for basic learning)

print(f"Starting observation: {observation}")
# Example output: [ 0.01234567 -0.00987654  0.02345678  0.01456789]
# [cart_position, cart_velocity, pole_angle, pole_angular_velocity]

episode_over = False
total_reward = 0

# One such action-observation exchange is called a timestep.
while not episode_over:
    # Choose an action: 0 = push cart left, 1 = push cart right
    action = env.action_space.sample()  # Random action for now - real agents will be smarter!

    # Take the action and see what happens
    observation, reward, terminated, truncated, info = env.step(action)

    # reward: +1 for each step the pole stays upright
    # terminated: True if pole falls too far (agent failed)
    # truncated: True if we hit the time limit (500 steps)

    total_reward += reward
    episode_over = terminated or truncated

# 直接使用 env.render() 获取整个episode的帧列表
save_video(
    frames=env.render(), # 获取帧列表
    video_folder="videos",
    fps=env.metadata["render_fps"], # 从环境元数据中获取FPS，若报错可手动指定，如 fps=30[reference:3]
    name_prefix="manual_save",
)

print(f"Episode finished! Total reward: {total_reward}")
env.close()

import gymnasium as gym

# Discrete action space (button presses)
env = gym.make("CartPole-v1")
print(f"Action space: {env.action_space}")  # Discrete(2) - left or right
print(f"Sample action: {env.action_space.sample()}")  # 0 or 1

# Box observation space (continuous values)
print(f"Observation space: {env.observation_space}")  # Box with 4 values
# Box([-4.8, -inf, -0.418, -inf], [4.8, inf, 0.418, inf])
print(f"Sample observation: {env.observation_space.sample()}")  # Random valid observation