ml4cps.control.base module

class ml4cps.control.base.Agent(policy, gamma)

Bases: object

class ml4cps.control.base.EnvironmentTA(automaton)

Bases: Env

Custom Environment that follows Gymnasium interface

property action_space

close()

Clean up resources if necessary.

property episode_length

expected_cum_reward(policy, discounted=True, max_depth=2)

metadata: dict[str, Any] = {'render_fps': 30, 'render_modes': ['human']}

render(mode='human')

Render the environment. No-op in this example.

reset(seed=None, options=None)

Reset the environment to an initial state and return the initial observation.

property state

step(action)

Take an action and return the next observation, reward, done, and info.