Obtain action from agent or actor representation given environment observations
returns the action derived from the policy of a reinforcement learning agent given
environment observations.agentAction
= getAction(agent
,obs
)
returns the action derived from policy representation actorAction
= getAction(actorRep
,obs
)actorRep
given
environment observations obs
.
[
returns the updated state of the actor representation when the actor uses a recurrent
neural network as a function approximator.actorAction
,nextState
] = getAction(actorRep
,obs
)