From 08af2a2f3b438934ace60b688c00c7e9169637b9 Mon Sep 17 00:00:00 2001 From: karpathy Date: Sun, 19 Apr 2015 12:48:45 -0700 Subject: [PATCH] adding github ribbons --- gridworld_dp.html | 2 ++ gridworld_td.html | 3 +++ index.html | 5 +++++ puckworld.html | 3 +++ waterworld.html | 3 +++ 5 files changed, 16 insertions(+) diff --git a/gridworld_dp.html b/gridworld_dp.html index f66db98..64bd4f5 100644 --- a/gridworld_dp.html +++ b/gridworld_dp.html @@ -428,6 +428,8 @@ + Fork me on GitHub +
diff --git a/gridworld_td.html b/gridworld_td.html index c1d19f8..1932791 100644 --- a/gridworld_td.html +++ b/gridworld_td.html @@ -556,6 +556,9 @@ + + Fork me on GitHub +
diff --git a/index.html b/index.html index 8937a39..0bc24b9 100644 --- a/index.html +++ b/index.html @@ -48,6 +48,9 @@ + + Fork me on GitHub +
@@ -122,6 +125,8 @@

REINFORCEjs

In other words, you pass the agent some vector and it gives you an action. Then you reward or punish its behavior with the `reward` signal. The agent will over time tune its parameters to maximize the rewards it obtains. +The full source code is on Github under the MIT license. +






diff --git a/puckworld.html b/puckworld.html index c563b49..17d5be9 100644 --- a/puckworld.html +++ b/puckworld.html @@ -454,6 +454,9 @@ + + Fork me on GitHub +
diff --git a/waterworld.html b/waterworld.html index ed5837e..ccb4609 100644 --- a/waterworld.html +++ b/waterworld.html @@ -325,6 +325,9 @@ + + Fork me on GitHub +