From cd23f6a7258a2f4c474ea2d6813d66cc00a84f15 Mon Sep 17 00:00:00 2001 From: Thomas Simonini Date: Mon, 12 Dec 2022 20:26:53 +0100 Subject: [PATCH 1/7] Update Bellman Latex equation quiz --- units/en/unit2/mid-way-quiz.mdx | 1 + 1 file changed, 1 insertion(+) diff --git a/units/en/unit2/mid-way-quiz.mdx b/units/en/unit2/mid-way-quiz.mdx index b1ffe3a..ded2617 100644 --- a/units/en/unit2/mid-way-quiz.mdx +++ b/units/en/unit2/mid-way-quiz.mdx @@ -38,6 +38,7 @@ The best way to learn and [to avoid the illusion of competence](https://www.cour **The Bellman equation is a recursive equation** that works like this: instead of starting for each state from the beginning and calculating the return, we can consider the value of any state as: \\(Rt+1 + (\gamma * V(St+1)))\\ + The immediate reward + the discounted value of the state that follows From c54bb4605e81d01b1b59c5dc3e437d83abb6ac2a Mon Sep 17 00:00:00 2001 From: Thomas Simonini Date: Mon, 12 Dec 2022 20:38:45 +0100 Subject: [PATCH 2/7] Updated Bellman equation (latex not working) --- units/en/unit2/mid-way-quiz.mdx | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/units/en/unit2/mid-way-quiz.mdx b/units/en/unit2/mid-way-quiz.mdx index ded2617..c00a726 100644 --- a/units/en/unit2/mid-way-quiz.mdx +++ b/units/en/unit2/mid-way-quiz.mdx @@ -37,7 +37,8 @@ The best way to learn and [to avoid the illusion of competence](https://www.cour **The Bellman equation is a recursive equation** that works like this: instead of starting for each state from the beginning and calculating the return, we can consider the value of any state as: -\\(Rt+1 + (\gamma * V(St+1)))\\ +Bellman equation quiz + The immediate reward + the discounted value of the state that follows From 746b3e0a2d03593610f44215d217fa9e994020b2 Mon Sep 17 00:00:00 2001 From: Thomas Simonini Date: Mon, 12 Dec 2022 20:44:55 +0100 Subject: [PATCH 3/7] Update Bellman Latex equation quiz --- units/en/unit2/mid-way-quiz.mdx | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/units/en/unit2/mid-way-quiz.mdx b/units/en/unit2/mid-way-quiz.mdx index c00a726..86584bf 100644 --- a/units/en/unit2/mid-way-quiz.mdx +++ b/units/en/unit2/mid-way-quiz.mdx @@ -37,9 +37,7 @@ The best way to learn and [to avoid the illusion of competence](https://www.cour **The Bellman equation is a recursive equation** that works like this: instead of starting for each state from the beginning and calculating the return, we can consider the value of any state as: -Bellman equation quiz - - +Rt+1 + gamma * V(St+1) The immediate reward + the discounted value of the state that follows From 35088e1f598325300a025b5d90c35b3f5fb4b621 Mon Sep 17 00:00:00 2001 From: Thomas Simonini Date: Mon, 12 Dec 2022 20:53:14 +0100 Subject: [PATCH 4/7] Update Bellman Latex equation quiz --- units/en/unit2/mid-way-quiz.mdx | 1 + 1 file changed, 1 insertion(+) diff --git a/units/en/unit2/mid-way-quiz.mdx b/units/en/unit2/mid-way-quiz.mdx index 86584bf..abb4b8b 100644 --- a/units/en/unit2/mid-way-quiz.mdx +++ b/units/en/unit2/mid-way-quiz.mdx @@ -38,6 +38,7 @@ The best way to learn and [to avoid the illusion of competence](https://www.cour **The Bellman equation is a recursive equation** that works like this: instead of starting for each state from the beginning and calculating the return, we can consider the value of any state as: Rt+1 + gamma * V(St+1) + The immediate reward + the discounted value of the state that follows From 2ca9a92002483586475ca48b196db4d0a79671b7 Mon Sep 17 00:00:00 2001 From: Thomas Simonini Date: Tue, 13 Dec 2022 10:59:34 +0100 Subject: [PATCH 5/7] Update hands-on.mdx --- units/en/unit2/hands-on.mdx | 1 + 1 file changed, 1 insertion(+) diff --git a/units/en/unit2/hands-on.mdx b/units/en/unit2/hands-on.mdx index 58a2a57..4b30bb0 100644 --- a/units/en/unit2/hands-on.mdx +++ b/units/en/unit2/hands-on.mdx @@ -21,6 +21,7 @@ Thanks to a [leaderboard](https://huggingface.co/spaces/huggingface-projects/Dee [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/deep-rl-class/blob/master/notebooks/unit2/unit2.ipynb) + # Unit 2: Q-Learning with FrozenLake-v1 ⛄ and Taxi-v3 🚕 Unit 2 Thumbnail From 95b869b3e6edb133dfca5a13248483674a332eab Mon Sep 17 00:00:00 2001 From: Thomas Simonini Date: Tue, 13 Dec 2022 11:07:58 +0100 Subject: [PATCH 6/7] Update hands-on.mdx --- units/en/unit2/hands-on.mdx | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/units/en/unit2/hands-on.mdx b/units/en/unit2/hands-on.mdx index 4b30bb0..08c63d7 100644 --- a/units/en/unit2/hands-on.mdx +++ b/units/en/unit2/hands-on.mdx @@ -1,10 +1,10 @@ # Hands-on [[hands-on]] - + From 3080ad3fc10b550cd74fdd9f93113252938931d5 Mon Sep 17 00:00:00 2001 From: Thomas Simonini Date: Tue, 13 Dec 2022 16:02:56 +0100 Subject: [PATCH 7/7] Update hands-on.mdx --- units/en/unit1/hands-on.mdx | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/units/en/unit1/hands-on.mdx b/units/en/unit1/hands-on.mdx index 078b3ec..2c65154 100644 --- a/units/en/unit1/hands-on.mdx +++ b/units/en/unit1/hands-on.mdx @@ -1,4 +1,5 @@ -# Hands on [[hands-on]] +# Train your first Deep Reinforcement Learning Agent 🤖 [[hands-on]] +