|
| | | | |
| | | |
| Stat |
Members: 3645
Articles: 2'506'133
Articles rated: 2609
26 April 2024 |
|
| | | | |
|
Article overview
| |
|
|
Revisiting Fundamentals of Experience Replay | | William Fedus
; Prajit Ramachandran
; Rishabh Agarwal
; Yoshua Bengio
; Hugo Larochelle
; Mark Rowland
; Will Dabney
; | | Date: |
13 Jul 2020 | | Abstract: | Experience replay is central to off-policy algorithms in deep reinforcement
learning (RL), but there remain significant gaps in our understanding. We
therefore present a systematic and extensive analysis of experience replay in
Q-learning methods, focusing on two fundamental properties: the replay capacity
and the ratio of learning updates to experience collected (replay ratio). Our
additive and ablative studies upend conventional wisdom around experience
replay -- greater capacity is found to substantially increase the performance
of certain algorithms, while leaving others unaffected. Counterintuitively we
show that theoretically ungrounded, uncorrected n-step returns are uniquely
beneficial while other techniques confer limited benefit for sifting through
larger memory. Separately, by directly controlling the replay ratio we
contextualize previous observations in the literature and empirically measure
its importance across a variety of deep RL algorithms. Finally, we conclude by
testing a set of hypotheses on the nature of these performance benefits. | | Source: | arXiv, 2007.6700 | | Services: | Forum | Review | PDF | Favorites | |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
browser Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)
|
| |
|
|
|
|
News, job offers and information for researchers and scientists:
| |
REGISTER