cleanup

DeepReinforcementLearning · Jul 11, 2020 · 998de51 · 998de51
1 parent 3d32324
commit 998de51
Show file tree

Hide file tree

Showing 31 changed files with 5,414 additions and 1,580 deletions.
diff --git a/Appendix/Appendix.ipynb b/Appendix/Appendix.ipynb
diff --git a/Chapter 10/Ch10_book.ipynb b/Chapter 10/Ch10_book.ipynb
@@ -186,7 +186,7 @@
     "    correct[[rows,yt.detach().long()]] = 1.\n",
     "    loss = lossfn(pred,yt)\n",
     "    loss.backward()\n",
-    "opt.step()"
+    "    opt.step()"
    ]
   },
   {
@@ -535,9 +535,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python [conda env:deeprl]",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "conda-env-deeprl-py"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -549,9 +549,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.7.4"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }
diff --git a/Chapter 5/avg_rewards.pdf b/Chapter 5/avg_rewards.pdf
diff --git a/Chapter 5/avg_rewards.png b/Chapter 5/avg_rewards.png
diff --git a/Chapter 5/avg_rewards_Nstep.pdf b/Chapter 5/avg_rewards_Nstep.pdf
diff --git a/Chapter 5/avg_rewards_Nstep.png b/Chapter 5/avg_rewards_Nstep.png
diff --git a/Chapter 6/dqn_1_loss_plot.pdf b/Chapter 6/dqn_1_loss_plot.pdf
diff --git a/Chapter 6/simulator_loss_plot.png b/Chapter 6/simulator_loss_plot.png
diff --git a/Chapter 9/Ch9 Mean Field Q-learning.ipynb b/Chapter 9/Ch9 Mean Field Q-learning.ipynb
diff --git a/Chapter 9/Ch9_book.ipynb b/Chapter 9/Ch9_book.ipynb
@@ -897,9 +897,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python [conda env:deeprl]",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "conda-env-deeprl-py"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -911,9 +911,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.7.4"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }
diff --git a/Environments/MAgent b/Environments/MAgent
diff --git a/Errata.md b/Errata.md
@@ -0,0 +1,44 @@
+# Errata
+Here we keep an updated list of book errata listed by chapter. The errata will be addressed periodically in the eBook and liveBook versions and less frequently in print versions. We highly recommend using the GitHub code when following along the book as it is very difficult to maintain code within the book text.
+
+## Chapter 2
+
+### Section 2.4.1
+Code should be:
+>>> x = torch.Tensor([2,4]) #input data
+>>> m = torch.randn(2, requires_grad=True) #parameter 1
+>>> b = torch.randn(1, requires_grad=True) #parameter 2
+>>> y = m*x+b #linear model
+>>> y_known = torch.Tensor([5,9])
+>>> loss = (torch.sum(y_known - y))**2 #loss function
+>>> loss.backward() #calculate gradients
+>>> m.grad
+tensor([ -51.9402, -103.8803])
+
+### Listing 2.10
+Code should be:
+def train(env, epochs=10000, learning_rate=1e-3):
+
+### Section 2.5
+Text should say: “When we train this network for 10,000 epochs”
+
+### In Summary, in bullet point 5
+“with probability ε – 1” should be “with probability 1 - ε “
+
+## Chapter 3
+
+### Listing 3.8 
+First line of code should be: from IPython.display import clear_output
+
+
+## Chapter 4
+
+
+
+
+
+
+
+
+
+
diff --git a/Errata/Chapter 2.ipynb b/Errata/Chapter 2.ipynb
diff --git a/Errata/Chapter 3.ipynb b/Errata/Chapter 3.ipynb
diff --git a/Errata/Chapter 4.ipynb b/Errata/Chapter 4.ipynb