getMaxQValue
Obtain maximum estimated value over all possible actions from a Q-value function critic with discrete action space, given environment observations
Since R2020a
Syntax
Description
[
evaluates the discrete-action-space Q-value function critic
maxQ
,maxActionIndex
] = getMaxQValue(qValueFcnObj
,obs
)qValueFcnObj
and returns the maximum estimated value over all
possible actions maxQ
, with the corresponding action index
maxActionIndex
, given environment observations
obs
.
[
also returns the updated state of maxQ
,maxActionIndex
,state
] = getMaxQValue(___)qValueFcnObj
when it contains a
recurrent neural network.
Examples
Input Arguments
Output Arguments
Version History
Introduced in R2020a