Comment on page
PrioritizedReplay
Prioritized Experience Replay (PER) extends from Replay by calculating prioritization for sampling experiences based on errors in Q-values estimation.
Suitable for off-policy algorithms.
Refer to the class documentation and example memory spec from the source: slm_lab/agent/memory/prioritized.py#L87-L104
This specification creates a PrioritizedReplay (off-policy) memory with a maximum capacity of 10,000 elements, with a batch size of 32, and CER is disabled. The
alpha
and epsilon
parameters are specific to PER in computing the errors.{
...
"agent": [{
"memory": {
"name": "PrioritizedReplay",
"alpha": 0.6,
"epsilon": 0.001,
"batch_size": 32,
"max_size": 10000,
"use_cer": false
}
}],
...
}
Last modified 2yr ago