Aurélien Geron
|
90e53af92c
|
Install gym[box2d] on Colab for LunarLander-v2 policy gradients exercise solution
|
2021-03-20 10:46:02 +13:00 |
|
Aurélien Geron
|
9af016e341
|
Remove redundant heading for LunarLander-v2 policy gradients exercise solution
|
2021-03-20 10:40:02 +13:00 |
|
Aurélien Geron
|
cfd0837f5c
|
Add LunarLander-v2 Policy Gradients exercise solution
|
2021-03-20 10:04:52 +13:00 |
|
Aurélien Geron
|
e9b5dce122
|
Fix auto-fire, add exercises, explain Space Invaders delta
|
2021-03-18 22:16:38 +13:00 |
|
Aurélien Geron
|
c98ee19363
|
Fix AtariPreprocessingWithAutoFire typo
|
2021-03-10 10:45:24 +13:00 |
|
Aurélien Geron
|
dd94101c5d
|
Speed up training: I tuned learning rate for DQN variants, and added auto-FIRE for Blockout. Fixes #117
|
2021-03-09 22:21:08 +13:00 |
|
Aurélien Geron
|
5c8843a53b
|
Merge pull request #290 from 8bitmp3/patch-1
Update (small) the reinforcement learning chapter
|
2021-03-02 12:11:47 +13:00 |
|
B D
|
64f0e05a94
|
Minor change on greedy policy variable usage
Chap 18, why not using directly the 'n_outputs' variable defined earlier, instead of hardcoded '2'
|
2021-02-28 12:02:23 +01:00 |
|
Aurélien Geron
|
749817ccfa
|
Update libraries to latest version, including TensorFlow 2.4.1 and Scikit-Learn 0.24.1
|
2021-02-18 11:59:02 +13:00 |
|
Aurélien Geron
|
8ebdcffc6b
|
Work around TF Agents issue: env.step(1) => env.step(np.array(1))
|
2020-11-23 16:52:37 +13:00 |
|
8bitmp3
|
80f6cb27c0
|
Update (small) the reinforcement learning chapter
|
2020-10-17 15:04:51 +01:00 |
|
Aurélien Geron
|
7b3d280a86
|
Fix error in commented out code, fixes #89
|
2020-03-31 21:39:51 +13:00 |
|
Aurélien Geron
|
cd4e2e1313
|
Add comment about the reshape operation from the training_step function
|
2020-03-12 22:51:36 +13:00 |
|
Aurélien Geron
|
49715d4b74
|
Fix bug in training_step: target_Q_values must be a column vector
|
2020-03-12 22:47:22 +13:00 |
|
Aurélien Geron
|
d6fbc91cf2
|
Upgrade packages, and add environment-windows.yml
|
2019-12-14 18:58:01 +08:00 |
|
Aurélien Geron
|
88dccccd5f
|
Make notebooks 14 to 19 runnable in Colab without changes
|
2019-11-06 21:06:55 +08:00 |
|
Aurélien Geron
|
d8971f1767
|
Fix os.join() => os.path.join()
|
2019-10-12 18:05:41 +09:30 |
|
Aurélien Geron
|
4c3b7b9b06
|
Save agent's breakout performance to an animated gif
|
2019-05-28 09:30:16 +08:00 |
|
Aurélien Geron
|
3ef350ab4c
|
Fix figure name and clarify a couple code examples
|
2019-05-27 20:35:00 +08:00 |
|
Aurélien Geron
|
c5f4b41cf5
|
Fix breakout plot
|
2019-05-26 23:56:49 +08:00 |
|
Aurélien Geron
|
2edbb6e9d4
|
Add Reinforcement Learning notebook
|
2019-05-26 23:30:39 +08:00 |
|
Aurélien Geron
|
73a36f335f
|
Add warning about TF issue regarding DenseFeatures and the Functional API, fixes #6
|
2019-05-15 20:23:24 +08:00 |