Skip to content

Conversation

LegionAtol
Copy link
Contributor

No description provided.

…le based on how many controls there are. using mesolve with QobjEvo object _H
_infidelity() more general
# Define action and observation spaces (Gym)
#self.action_space = spaces.Box(low=-1, high=1, shape=(1,), dtype=np.float32) # Continuous action space from -1 to +1, as suggested from gym
self.action_space = spaces.Box(low=-1, high=1, shape=(len(self._Hc_lst[0]),), dtype=np.float32)
self.observation_space = spaces.Box(low=-1, high=1, shape=(4,), dtype=np.float32) # Observation space, |v> have 2 real and 2 imaginary numbers -> 4
Copy link
Collaborator

@flowerthrower flowerthrower Aug 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
self.observation_space = spaces.Box(low=-1, high=1, shape=(4,), dtype=np.float32) # Observation space, |v> have 2 real and 2 imaginary numbers -> 4
self.observation_space = spaces.Box(low=-1, high=1, shape=(dim_m, dim_n, 2), dtype=np.float32) # Observation space for complex matrix or state vector

@flowerthrower
Copy link
Collaborator

@LegionAtol can we close this PR?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants