Package ai.djl.modality.rl

Class LruReplayBuffer

java.lang.Object

ai.djl.modality.rl.LruReplayBuffer

All Implemented Interfaces:

ReplayBuffer

public class LruReplayBuffer
extends Object
implements ReplayBuffer

A simple ReplayBuffer that randomly selects across the whole buffer, but always removes the oldest items in the buffer once it is full.

Constructor Summary

Constructors

Constructor	Description
LruReplayBuffer(int batchSize, int bufferSize)	Constructs a LruReplayBuffer.

Method Summary

Modifier and Type	Method	Description
void	addStep(RlEnv.Step step)	Adds a new step to the buffer.
RlEnv.Step[]	getBatch()	Returns a batch of steps from this buffer.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

LruReplayBuffer

public LruReplayBuffer(int batchSize,
 int bufferSize)

Constructs a LruReplayBuffer.

Parameters:

batchSize - the number of steps to train on per batch

bufferSize - the number of steps to hold in the buffer

Method Details

getBatch

public RlEnv.Step[] getBatch()

Returns a batch of steps from this buffer.

Specified by:

getBatch in interface ReplayBuffer

Returns:

a batch of steps from this buffer

addStep

public void addStep(RlEnv.Step step)

Adds a new step to the buffer.

Specified by:

addStep in interface ReplayBuffer

Parameters:

step - the step to add