chemistrylab.lab

chemistrylab.lab.lab

class chemistrylab.lab.lab.Lab(render_mode: Optional[str] = None, max_num_vessels: int = 100)

Bases: Env, ABC

The lab class is meant to be a gym environment so that an agent can figure out how to synthesize different chemicals

action_space: spaces.Space[ActType]

load_distillation_bench(index)

this function returns the distillation environment that the agent has selected

Parameters:

index (the index of the agent to be run) –

Return type:

the gym environment that has been loaded

load_extraction_bench(index)

this function returns the extraction environment that the agent has selected

Parameters:

index (the index of the agent to be run) –

Return type:

the gym environment that has been loaded

load_reaction_bench(index: int)

this function returns the reaction environment that the agent has selected

Parameters:

index (the index of the agent to be run) –

Return type:

the gym environment that has been loaded

observation_space: spaces.Space[ObsType]

register_agent(bench: str, name: str, agent: object)

a function that registers an agent for a specified bench

Parameters:

• bench (the bench for which the agent will be registered) –

• name (the name of the agent to be registered) –

• agent (the agent itself derived from the agent class) –

Return type:

None

reset()

this function resets the shelf and gets rid of all the currently stored vessels :rtype: None

run_bench(bench, env_index, vessel_index, agent_index=0, custom_agent=None)

this function works as a wrapper for the lab environment and allows for an agent to specify what environment they wish to run and with what vessel and agent

Parameters:

• bench –

• env_index –

• vessel_index –

• agent_index –

• custom_agent –

step(action: list)

This function takes in an agents command and deconstructs the command and runs the appropriate environment with the specified bench, environment, vessel, and agent :param action: :type action: [list, np.array]: this parameter specifies the action the agent takes :param action: :type action: [bench_id, environment_id, vessel_id, agent_id]

Return type:

None

chemistrylab.lab.manager

class chemistrylab.lab.manager.Manager(mode='custom', agent=None)

Bases: object

create_new_vessel()

Method to create a new vessel and place the new vessel on the shelf.

Parameters:

None –

Return type:

None

Raises:

None –

list_vessels()

Method to list all the vessels available on the shelf and their contents.

Parameters:

None –

Return type:

None

Raises:

None –

load_bench(bench, env_index, vessel_index, agent)

Method to load the specified bench based on the environment, vessel, and agent parameters.

Parameters:

• bench (str) – The name of the bench that is to be loaded.

• env_index (np.int64) – The index corresponding to the requested bench environment that is to be set up.

• vessel_index (np.int64) – The index corresponding to the requested vessel that is to be set up.

• agent (np.int64) – The index corresponding to the requested agent that is to be set up.

Return type:

None

Raises:

None –

load_vessel(path)

Method to load a vessel from a specified path.

Parameters:

path (str) – The directory path to a valid pickle file containing a vessel object.

Return type:

None

Raises:

IOError – Raised if the specified file path does not correspond to a valid vessel pickle file.

register_agent(name: str, agent: object)

Allows the user to add a lab agent to the manager environment. Added lab agents can then use to perform actions in the lab environment.

Parameters:

• name (str) – The name of the agent to be registered.

• agent (agent.Agent) – The class representation of the agent to be registered.

Return type:

None

Raises:

None –

register_bench_agent(bench: str, name: str, agent: object)

Method to allow the user to add bench-specific agents to the lab environment. Added bench agents can then be used in order to perform actions in a bench

Parameters:

• bench (str) – The name of the bench to which the agent is being assigned.

• name (str) – The name of the agent to be registered.

• agent (agent.Agent) – The class representation of the agent to be registered.

Return type:

None

Raises:

None –

run()

Method to run the specified agent or human mode based on the parameters passed to the Manager class.

Parameters:

None –

Return type:

None

Raises:

None –

save_vessel()

Method to save a human-specified vessel.

Parameters:

None –

Return type:

None

Raises:

None –

chemistrylab.lab.shelf

class chemistrylab.lab.shelf.Shelf(vessels, n_working=1)

Bases: object

The shelf class holds vessels from experiments.

pop, __getitem__, __delitem__, and append are implemented so shelves can be used similar to a list of vessels

append(vessel: Vessel)

get_vessels()

get_working_vessels()

Returns a tuple of the ‘working’ vessels used for observations and rewards.

load_vessel(path: str)

TODO: Implement this Args: - path (str): the path to the vessel that is to be loaded

pop()

reset(target=None)

TODO: Update this along with __init__ Resets the shelf to it’s initial state

class chemistrylab.lab.shelf.VariableShelf(variable_vessels: list, fixed_vessels: list, n_working=1)

Bases: Shelf

Shelf which is given a set of fixed and variable vessels. On reset the original vessels are deepcopied into new vessel objects

reset(target=None)

TODO: Update this along with __init__ Resets the shelf to it’s initial state