ai.djl.modality.rl.agent

Interface RlAgent

All Known Implementing Classes:

EpsilonGreedy, QAgent

public interface RlAgent

An RlAgent is the model or technique to decide the actions to take in an RlEnv.

Method Summary

Modifier and Type	Method and Description
NDList	chooseAction(RlEnv env, boolean training) Chooses the next action to take within the RlEnv.
void	trainBatch(RlEnv.Step[] batchSteps) Trains this RlAgent on a batch of RlEnv.Steps.

Method Detail

chooseAction

NDList chooseAction(RlEnv env,
                    boolean training)

Chooses the next action to take within the RlEnv.

Parameters:

env - the current environment

training - true if the agent is currently traning

Returns:

the action to take

trainBatch

void trainBatch(RlEnv.Step[] batchSteps)

Trains this RlAgent on a batch of RlEnv.Steps.

Parameters:

batchSteps - the steps to train on