RLSimion
RLSimion.exe inputfile.simion.exp [-pipe=pipename] [-printIOfiles]
The pipename should be given if we want to redirect the output to a named pipe (i.e. when launched remotely via a HerdAgent). The flag -printIOfiles prints in the standard output the inputs/outputs of a given experiment without actually running the experiment.
An experiment consists of a series of episodes (epochs), which may be used for training or evaluation. First, the number of training episodes is given (may be 0 if we only want to evaluate a controller), then how often evaluations will be done (after how many training episodes), and finally, how many episodes will be used for evaluation. Certain worlds may require more complex evaluations: for example, when evaluating a wind-turbine controller we may want to measure performance with different wind speeds. These worlds need to call
CSimionApp::get()->pEpisode->setNumEpisodesPerEvaluation(nEpisodesPerEvaluation)
Evaluation will always take place at the very beginning of the learning process, at the end (unless the number of training episodes is 0) and every n training episodes.
Consider the following example: the number of training episodes is 5, evaluation is done every 2 training episodes, and each evaluation consists of a single episode. The total number of episodes would be 5 + ((5/2)+1)*1= 8. The values returned by the following CExperiment methods would be:
On the other hand, if we use 2 episodes per evaluation, the number of episodes would be 5 + ((5/2)+1)*2= 11. The following values would be obtained:
Parameters that are to be set from GUI application (Badger) are embbeded within the source code. They get their value from an XML node (CConfigNode) on construction:
- INT_PARAM
- DOUBLE_PARAM
- BOOL_PARAM
- STRING_PARAM
- DIR_PATH_PARAM
- FILE_PATH_PARAM
- ENUM_PARAM
- STATE_VARIABLE
- ACTION_VARIABLE
- CHILD_OBJECT
- CHILD_OBJECT_FACTORY
- MULTI_VALUE
- MULTI_VALUE_FACTORY
- MULTI_VALUE_SIMPLE_PARAM
- CHOICE