EDU.gatech.cc.is.clay
Class i_StepLearner_id
java.lang.Object
|
+--EDU.gatech.cc.is.clay.Node
|
+--EDU.gatech.cc.is.clay.NodeScalar
|
+--EDU.gatech.cc.is.clay.NodeInt
|
+--EDU.gatech.cc.is.clay.i_StepLearner_id
- public class i_StepLearner_id
- extends NodeInt
A node that uses a reinforcement learning module to learn
over time which output to select, given the current state
and reward.
Differs from i_Learner_id because it calls the learner each step.
For detailed information on how to configure behaviors, see the
Clay page.
Copyright
(c)1997, 1998 Tucker Balch
Method Summary |
int |
Value(long timestamp)
Get the value of the node. |
Methods inherited from class EDU.gatech.cc.is.clay.Node |
initTrial |
Methods inherited from class java.lang.Object |
clone,
equals,
finalize,
getClass,
hashCode,
notify,
notifyAll,
toString,
wait,
wait,
wait |
i_StepLearner_id
public i_StepLearner_id(i_ReinforcementLearner_id m,
long ms,
NodeInt e1,
NodeScalar e2)
- Instantiate a reinforcement learning node with a specified
learning module.
- Parameters:
m
- i_ReinforcementLearning_id, the learning module.ms
- long, maximum time to stay in one state.e1
- NodeInt, a node that provides state information.e2
- NodeScalar, a node that provides the reinforcement
signal.
Value
public int Value(long timestamp)
- Get the value of the node.
- Overrides:
- Value in class NodeInt
- Parameters:
timestamp
- long, the time of the request.