From a05ffc33b4a6de64aeeda17a462f64f48e067587 Mon Sep 17 00:00:00 2001 From: amocken <48198083+amocken@users.noreply.github.com> Date: Tue, 28 Feb 2023 20:39:40 +0800 Subject: [PATCH] Update rl_intro2.rst spelling mistake --- docs/spinningup/rl_intro2.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/spinningup/rl_intro2.rst b/docs/spinningup/rl_intro2.rst index 1fb3597b2..c0f32d139 100644 --- a/docs/spinningup/rl_intro2.rst +++ b/docs/spinningup/rl_intro2.rst @@ -100,7 +100,7 @@ Unlike model-free RL, there aren't a small number of easy-to-define clusters of * The `ExIt`_ algorithm uses this approach to train deep neural networks to play Hex. * `AlphaZero`_ is another example of this approach. -**Data Augmentation for Model-Free Methods.** Use a model-free RL algorithm to train a policy or Q-function, but either 1) augment real experiences with fictitious ones in updating the agent, or 2) use *only* fictitous experience for updating the agent. +**Data Augmentation for Model-Free Methods.** Use a model-free RL algorithm to train a policy or Q-function, but either 1) augment real experiences with fictitious ones in updating the agent, or 2) use *only* fictitious experience for updating the agent. * See `MBVE`_ for an example of augmenting real experiences with fictitious ones. * See `World Models`_ for an example of using purely fictitious experience to train the agent, which they call "training in the dream."