From 3a9d26c8b131f132e05f45b4b5a82df62540d7c6 Mon Sep 17 00:00:00 2001 From: Rodrigo de Salvo Braz Date: Tue, 20 Feb 2024 22:10:43 -0800 Subject: [PATCH] Add nbviewer link to DQN tutorial Summary: GitHub does not always render notebooks properly, so we add a link to an nbviewer rendering of this notebook. Reviewed By: jb3618columbia Differential Revision: D53982457 fbshipit-source-id: 4cb7aa84b1aa60cd0a505a860111353ce133aada --- .../sequential_decision_making/DQN_and_DoubleDQN_example.ipynb | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tutorials/sequential_decision_making/DQN_and_DoubleDQN_example.ipynb b/tutorials/sequential_decision_making/DQN_and_DoubleDQN_example.ipynb index 10d791dd..a6e87b4c 100644 --- a/tutorials/sequential_decision_making/DQN_and_DoubleDQN_example.ipynb +++ b/tutorials/sequential_decision_making/DQN_and_DoubleDQN_example.ipynb @@ -8,6 +8,8 @@ "source": [ "# Using DQN and Double DQN in Pearl with different neural network instantiations.\n", "\n", + "Here is a [better rendering](https://nbviewer.org/github/facebookresearch/Pearl/blob/main/tutorials/sequential_decision_making/DQN_and_DoubleDQN_example.ipynb) of this notebook on [nbviewer](https://nbviewer.org/).\n", + "\n", "- The purpose of this tutorial is twofold. First, it illustrates how users can use implementations of value based methods, for example, DQN and Double DQN, in Pearl. We use a simple Gym environment for illustration.\n", "\n", "- Second, it illustrates how users can instantiate a neural network (outside of a Pearl Agent) and pass it to different policy learners in Pearl. For both examples (DQN and Double DQN), we use an instantiation of `QValueNetworks` outside of the Pearl Agent. The default way right now is to instantiate a Q-value network inside the agent's policy learner.\n",