Aurélien Geron
|
3af8bcd1bb
|
Update ReplayMemory class and add a short description
|
2018-05-09 16:54:17 +02:00 |
|
Aurélien Geron
|
c6b424931a
|
Merge pull request #204 from NileshPS/master
Ch 16. Using native python list instead of deque for storing experience, increases sampling performance considerably.
|
2018-05-09 15:34:12 +02:00 |
|
Aurélien Geron
|
10bc49aa91
|
Add solution to exercise 16.8 (BipedalWalker-v2 using Policy Gradients)
|
2018-05-09 15:25:49 +02:00 |
|
Aurélien Geron
|
e05d4b36ac
|
tf.contrib.layers.variance_scaling_initializer moved to tf.variance_scaling_initializer
|
2018-05-08 19:40:05 +02:00 |
|
Nilesh PS
|
aaa5246d9c
|
use ReplayMemory
|
2018-03-28 20:26:35 +05:30 |
|
Nilesh PS
|
16e8a8cf61
|
use list with circular indexing instead of deque as the replay buffer
|
2018-03-28 19:57:26 +05:30 |
|
ziembla
|
c4f82f3621
|
Don't try OpenAI rendering in Chapter 16 Section 3
|
2018-03-21 22:35:10 +01:00 |
|
Aurélien Geron
|
8a6c7da0a9
|
Scale X_state down to [-1, 1] range in chapter 16
|
2017-11-09 16:35:44 +01:00 |
|
Aurélien Geron
|
7686839b36
|
Use int8 instead of float64 to represent pixel values: divides RAM footprint by 8
|
2017-11-09 13:17:24 +01:00 |
|
Aurélien Geron
|
422b2c0e10
|
Larger replay memory
|
2017-09-26 14:50:09 +02:00 |
|
Aurélien Geron
|
edf4006ab4
|
Add example preprocessing for Breakout game in notebook for chapter 16
|
2017-09-25 14:08:42 +02:00 |
|
Aurélien Geron
|
02c41c9bc0
|
Fix errors in the MsPacman DQN in the notebook for chapter 16
|
2017-09-25 14:08:10 +02:00 |
|
Jason Rys
|
dc901e0ada
|
Fix typos
|
2017-08-19 08:01:55 -07:00 |
|
Aurélien Geron
|
48718eff9d
|
Use np.random.set_seed(42) and tf.set_random_seed(42) to make notebook's output constant
|
2017-06-08 15:44:00 +02:00 |
|
Aurélien Geron
|
326d32cae0
|
Use tf.layers instead of tf.contrib.layers
|
2017-04-30 10:21:27 +02:00 |
|
Aurélien Geron
|
fe552bbbed
|
Sadly had to remove binder support, because it is too unreliable and has been down for a month.
|
2017-03-04 11:15:52 +01:00 |
|
Aurélien Geron
|
d8176ec2cb
|
Upgrade notebooks to TensorFlow 1.0.0
|
2017-02-17 11:51:26 +01:00 |
|
Aurélien Geron
|
30ca2b86d7
|
Change xvfb comment
|
2016-11-25 09:34:55 +01:00 |
|
Aurélien Geron
|
9e414b6d64
|
Remove warnings and fix path in ch16
|
2016-11-05 14:29:24 +01:00 |
|
Aurélien Geron
|
6714ec2979
|
Add Policy Gradients and DQN to RL notebook
|
2016-10-23 15:32:33 +02:00 |
|
Aurélien Geron
|
9224775d79
|
Catch all exceptions when loading gl_info
|
2016-10-09 11:22:36 +02:00 |
|
Aurélien Geron
|
f6298cb03b
|
Fix CartPole rendering issue in chapter 16
|
2016-10-09 11:01:56 +02:00 |
|
Aurélien Geron
|
05ffb99e10
|
Add reinforcement learning notebook (in progress)
|
2016-10-08 22:17:45 +02:00 |