update readme

README.md

@@ -13,7 +13,6 @@ See some [examples](examples) to learn about the framework:
 + [Fully-convolutional Network for Holistically-Nested Edge Detection(HED)](examples/HED)
 + [Spatial Transformer Networks on MNIST addition](examples/SpatialTransformer)
 + [Visualize Saliency Maps by Guided ReLU](examples/Saliency)
-+ [Similarity Learning on MNIST](examples/SimilarityLearning)
 
 ### Reinforcement Learning:
 + [Deep Q-Network(DQN) variants on Atari games](examples/DeepQNetwork), including DQN, DoubleDQN, DuelingDQN.
@@ -21,6 +20,7 @@ See some [examples](examples) to learn about the framework:
 
 ### Unsupervised Learning:
 + [Generative Adversarial Network(GAN) variants](examples/GAN), including DCGAN, InfoGAN, Conditional GAN, WGAN, BEGAN, DiscoGAN, Image to Image.
++ [Similarity Learning on MNIST](examples/SimilarityLearning)
 
 ### Speech / NLP:
 + [LSTM-CTC for speech recognition](examples/CTC-TIMIT)

examples/A3C-Gym/train-atari.py

@@ -211,6 +211,7 @@ def get_config():
     master = MySimulatorMaster(namec2s, names2c, M)
     dataflow = BatchData(DataFromQueue(master.queue), BATCH_SIZE)
     return TrainConfig(
+        model=M,
         dataflow=dataflow,
         callbacks=[
             ModelSaver(),
@@ -218,13 +219,14 @@ def get_config():
             ScheduledHyperParamSetter('entropy_beta', [(80, 0.005)]),
             ScheduledHyperParamSetter('explore_factor',
                                       [(80, 2), (100, 3), (120, 4), (140, 5)]),
+            HumanHyperParamSetter('learning_rate'),
+            HumanHyperParamSetter('entropy_beta'),
             master,
             StartProcOrThread(master),
             PeriodicTrigger(Evaluator(EVAL_EPISODE, ['state'], ['policy']), every_k_epochs=2),
         ],
         session_creator=sesscreate.NewSessionCreator(
             config=get_default_sess_config(0.5)),
-        model=M,
         steps_per_epoch=STEPS_PER_EPOCH,
         max_epoch=1000,
     )

examples/README.md

@@ -13,7 +13,6 @@ Training examples with __reproducible__ and meaningful performance.
 + [Fully-convolutional Network for Holistically-Nested Edge Detection(HED)](HED)
 + [Spatial Transformer Networks on MNIST addition](SpatialTransformer)
 + [Visualize Saliency Maps by Guided ReLU](Saliency)
-+ [Similarity Learning on MNIST](SimilarityLearning)
 + Load a pre-trained [AlexNet](load-alexnet.py) or [VGG16](load-vgg16.py) model.
 + Load a pre-trained [Convolutional Pose Machines](ConvolutionalPoseMachines/).
 
@@ -22,7 +21,8 @@ Training examples with __reproducible__ and meaningful performance.
 + [Asynchronous Advantage Actor-Critic(A3C) with demos on OpenAI Gym](A3C-Gym)
 
 ## Unsupervised Learning:
-+ [Generative Adversarial Network(GAN) variants](GAN), including DCGAN, InfoGAN, Conditional GAN, WGAN, DiscoGAN, Image to Image.
++ [Generative Adversarial Network(GAN) variants](GAN), including DCGAN, InfoGAN, Conditional GAN, WGAN, BEGAN, DiscoGAN, Image to Image.
++ [Similarity Learning on MNIST](SimilarityLearning)
 
 ## Speech / NLP:
 + [LSTM-CTC for speech recognition](CTC-TIMIT)