Right now, action precision (alpha) in case of stochastic action sampling, is defaulted to alpha = 16.0 within the function of the control module sample_action(..., alpha = 16.0). Change this so that an instance of Agent.agent itself stores the action precision, and calls it in its method self.sample_action().
Right now, action precision (
alpha
) in case of stochastic action sampling, is defaulted toalpha = 16.0
within the function of thecontrol
modulesample_action(..., alpha = 16.0)
. Change this so that an instance ofAgent.agent
itself stores the action precision, and calls it in its methodself.sample_action()
.Originally posted by @helenegu in https://github.com/infer-actively/pymdp/discussions/4#discussioncomment-3018137