Template. Initializes the agent's learning behaviour A = LRN_INIT(A, INFO) Initializes the agent's learning behaviour. This function is a template and performs no operations. This function's input and output argument(s) must conform to the specifications below. Any actual implementation of this template must be coupled with an implementation of the lrn() template. Parameters: A - the agent INFO - a structure containing various informative data. This data comes mainly from the world implementation. The INFO structure will contain at least the following fields: 'episodic' - a flag signaling whether the task is episodic 'nagents' - the number of agents in the task 'statespacesize' - the size of the world state space 'actionspacesize'- the size of the joint action space 'imap' - a column vector specifying where in the world state vector the agent finds its own state and the common state of the world (i.e. state elements independent of other agents), and where on the joint action and reward vectors the agent finds its own action and reward. See world_info for the structure of some of these fields. In addition, the function has access to the learning parameters and index map of the agent, stored under fields 'learnparam' and 'indices'. This function should store the names of the volatile agent fields (i.e. the fields that are only relevant during learning) in a cell array field named 'volatile'. Global volatile variables is supported. Use the prefix "global:" in giving the volatile variable's name. Example: a.volatile = {'global:GLOBAL_DATA', 'localfield1', 'localfield2'}; See also lrn, agent_initlearn