From 15959539326c71dd2060f43aae74f601e786b962 Mon Sep 17 00:00:00 2001 From: Rootul Patel Date: Tue, 1 Jan 2019 20:40:57 -0500 Subject: [PATCH] SOTA -> state of the art I'm not sure what "SOTA" means but https://www.internetslang.com/SOTA-meaning-definition.asp indicates "State Of The Art" which seems clearer. --- docs/user/algorithms.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/user/algorithms.rst b/docs/user/algorithms.rst index 6275448f6..c0cce8cab 100644 --- a/docs/user/algorithms.rst +++ b/docs/user/algorithms.rst @@ -31,7 +31,7 @@ They are all implemented with `MLP`_ (non-recurrent) actor-critics, making them Why These Algorithms? ===================== -We chose the core deep RL algorithms in this package to reflect useful progressions of ideas from the recent history of the field, culminating in two algorithms in particular---PPO and SAC---which are close to SOTA on reliability and sample efficiency among policy-learning algorithms. They also expose some of the trade-offs that get made in designing and using algorithms in deep RL. +We chose the core deep RL algorithms in this package to reflect useful progressions of ideas from the recent history of the field, culminating in two algorithms in particular---PPO and SAC---which are close to state of the art on reliability and sample efficiency among policy-learning algorithms. They also expose some of the trade-offs that get made in designing and using algorithms in deep RL. The On-Policy Algorithms ------------------------