mlpy.agents.modules.FollowPolicyModule¶
-
class
mlpy.agents.modules.FollowPolicyModule(policies, niter=None, start=None)[source]¶ Bases:
mlpy.agents.modules.IAgentModuleThe follow policy agent module.
The follow policy agent module follows a given policy choosing the next action based on that policy.
Parameters: policies : array_like, shape (n, nfeatures, ni)
A list of policies (i.e., action sequences), where n is the number of policies, nfeatures is the number of action features, and ni is the sequence length.
niter : int, optional
The number of times each policy is repeated. Default is 1.
start : int, optional
The first policy to execute. Default is 0.
Attributes
midThe module’s unique identifier. Methods
change_policies(policies)Exchange the list of policies. enter(t)Enter the module and perform initialization tasks. execute(state)Execute the agent module. exit()Exit the module and perform cleanup tasks. get_next_action()Return the next action. is_complete()Check if the agent module has completed. load(filename)Load the state of the module from file. reset(t, **kwargs)Reset the module for the next iteration. save(filename)Save the current state of the module to file. terminate(value)Set the termination flag. update(dt)Update the module at every delta time step dt.