Fix a critical bug

Fix a critical bug at generating inputs. It’s difficult to locate.
suquark · Jan 27, 2017 · d355661 · d355661
1 parent 4148d88
commit d355661
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/RL/deepqlearn.js b/RL/deepqlearn.js
@@ -135,11 +135,12 @@ class DQN {
         var n = this.window_size;
         for (let k = 0; k < this.temporal_window; k++) {
             let state = this.state_window[n - 1 - k];
+            let action = this.action_window[n - 1 - k];
             // state
             w = w.concat(state);
             // action, encoded as 1-of-k indicator vector. We scale it up a bit because
             // we dont want weight regularization to undervalue this information, as it only exists once
-            let action1ofk = one_hot(this.num_actions, state, 1.0 * this.num_states);
+            let action1ofk = one_hot(this.num_actions, action, 1.0 * this.num_states);
             w = w.concat(action1ofk);
         }
         return w;

diff --git a/test_rl.html b/test_rl.html
@@ -130,7 +130,7 @@
     startlearn();
     goveryfast();
 
-    $.getJSON("RL/helper/saving2.json", function(json) {
+    $.getJSON("RL/helper/saving.json", function(json) {
         w.agent.brain.value_net.fromJSON(json);
         stoplearn();
         gonormal();