tokb23 / dqn Goto Github PK
View Code? Open in Web Editor NEWDQN implementation in Keras + TensorFlow + OpenAI Gym
dqn's People
Contributors
Stargazers
Watchers
Forkers
vyraun sherjilozair eddy0613 arpit15 nowke wiibrew zhuchiheng polinakoval mrleetree exception4u howl-anderson mehdibaha gqzhouslac yangyangl danielkaifeng wangpeng3891 davinnovation simonsroad sanfendu wangjianyong mastermstc shubhampachori12110095 davidliujiafeng rt1shnik jackshannon rugby0823 88d52bdba0366127fffca9dfa93895 a-blackfish fuxuliu jiangminmin cheunglei harry990 dorianhenault gajanan-vijay jiweixia12 fahim9898 lasdasdas liangzai951 hi-ai lizhuo-1994 petergaom enochkan cosastro ydeh22 molakesi123 nwpudjy li-sujudqn's Issues
error in running dqn and ddqn
python ddqn.py
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcurand.so locally
Using TensorFlow backend.
[2017-09-21 01:21:23,391] Making new env: Breakout-v0
ddqn.py:90: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(32, (8, 8), strides=(4, 4), activation="relu", input_shape=(4, 84, 84...)
model.add(Convolution2D(32, 8, 8, subsample=(4, 4), activation='relu', input_shape=(STATE_LENGTH, FRAME_WIDTH, FRAME_HEIGHT)))
Traceback (most recent call last):
File "ddqn.py", line 314, in
main()
File "ddqn.py", line 277, in main
agent = Agent(num_actions=env.action_space.n)
File "ddqn.py", line 58, in init
self.s, self.q_values, q_network = self.build_network()
File "ddqn.py", line 90, in build_network
model.add(Convolution2D(32, 8, 8, subsample=(4, 4), activation='relu', input_shape=(STATE_LENGTH, FRAME_WIDTH, FRAME_HEIGHT)))
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/keras/models.py", line 442, in add
layer(x)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/keras/engine/topology.py", line 602, in call
output = self.call(inputs, **kwargs)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/keras/layers/convolutional.py", line 164, in call
dilation_rate=self.dilation_rate)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 3164, in conv2d
data_format='NHWC')
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 640, in convolution
op=op)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 309, in with_space_to_batch
return op(input, num_spatial_dims, padding)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 632, in op
name=name)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 130, in _non_atrous_convolution
name=name)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 396, in conv2d
data_format=data_format, name=name)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2242, in create_op
set_shapes_for_outputs(ret)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1617, in set_shapes_for_outputs
shapes = shape_func(op)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1568, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn
debug_python_shape_fn, require_shape_fn)
File "/home/tushar/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/common_shapes.py", line 675, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Negative dimension size caused by subtracting 8 from 4 for 'conv2d_1/convolution' (op: 'Conv2D') with input shapes: [?,4,84,84], [8,8,84,32].
AMI
I can't find the AMI as:
AMI name is DQN-AMI, the ID is ami-c4a969a9, and the region is N. Virginia.
Is there another one?
ValueError: Negative dimension size caused by subtracting 8 from 4
I'm getting the error, ValueError: Negative dimension size caused by subtracting 8 from 4, when running dqn.py. What could be causing this?
[2016-12-15 00:50:34,381] Making new env: Breakout-v0
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/common_shapes.py", line 594, in call_cpp_shape_fn
status)
File "/usr/lib/python3.5/contextlib.py", line 66, in __exit__
next(self.gen)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors.py", line 463, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors.InvalidArgumentError: Negative dimension size caused by subtracting 8 from 4
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "dqn.py", line 312, in <module>
main()
File "dqn.py", line 275, in main
agent = Agent(num_actions=env.action_space.n)
File "dqn.py", line 58, in __init__
self.s, self.q_values, q_network = self.build_network()
File "dqn.py", line 90, in build_network
model.add(Convolution2D(32, 8, 8, subsample=(4, 4), activation='relu', input_shape=(STATE_LENGTH, FRAME_WIDTH, FRAME_HEIGHT)))
File "/usr/local/lib/python3.5/dist-packages/Keras-1.1.2-py3.5.egg/keras/models.py", line 294, in add
layer.create_input_layer(batch_input_shape, input_dtype)
File "/usr/local/lib/python3.5/dist-packages/Keras-1.1.2-py3.5.egg/keras/engine/topology.py", line 374, in create_input_layer
self(x)
File "/usr/local/lib/python3.5/dist-packages/Keras-1.1.2-py3.5.egg/keras/engine/topology.py", line 519, in __call__
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/usr/local/lib/python3.5/dist-packages/Keras-1.1.2-py3.5.egg/keras/engine/topology.py", line 573, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/usr/local/lib/python3.5/dist-packages/Keras-1.1.2-py3.5.egg/keras/engine/topology.py", line 155, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/usr/local/lib/python3.5/dist-packages/Keras-1.1.2-py3.5.egg/keras/layers/convolutional.py", line 465, in call
filter_shape=self.W_shape)
File "/usr/local/lib/python3.5/dist-packages/Keras-1.1.2-py3.5.egg/keras/backend/tensorflow_backend.py", line 1734, in conv2d
x = tf.nn.conv2d(x, kernel, strides, padding=padding)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 394, in conv2d
data_format=data_format, name=name)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 749, in apply_op
op_def=op_def)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 2382, in create_op
set_shapes_for_outputs(ret)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1783, in set_shapes_for_outputs
shapes = shape_func(op)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/common_shapes.py", line 596, in call_cpp_shape_fn
raise ValueError(err.message)
ValueError: Negative dimension size caused by subtracting 8 from 4
Error running
I'm getting this when cloning and running on Python 3.6.1, TensorFlow 1.2.1.
Using TensorFlow backend.
[2017-08-18 00:10:05,170] Making new env: Breakout-v0
dqn.py:90: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(32, (8, 8), activation="relu", input_shape=(4, 84, 84..., strides=(4, 4))`
model.add(Convolution2D(32, 8, 8, subsample=(4, 4), activation='relu', input_shape=(STATE_LENGTH, FRAME_WIDTH, FRAME_HEIGHT)))
Traceback (most recent call last):
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 671, in _call_cpp_shape_fn_impl
input_tensors_as_shapes, status)
File "/Users/schmatz/anaconda/lib/python3.6/contextlib.py", line 89, in __exit__
next(self.gen)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 8 from 4 for 'conv2d_1/convolution' (op: 'Conv2D') with input shapes: [?,4,84,84], [8,8,84,32].
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "dqn.py", line 312, in <module>
main()
File "dqn.py", line 275, in main
agent = Agent(num_actions=env.action_space.n)
File "dqn.py", line 58, in __init__
self.s, self.q_values, q_network = self.build_network()
File "dqn.py", line 90, in build_network
model.add(Convolution2D(32, 8, 8, subsample=(4, 4), activation='relu', input_shape=(STATE_LENGTH, FRAME_WIDTH, FRAME_HEIGHT)))
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/keras/models.py", line 436, in add
layer(x)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/keras/engine/topology.py", line 596, in __call__
output = self.call(inputs, **kwargs)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/keras/layers/convolutional.py", line 164, in call
dilation_rate=self.dilation_rate)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 3156, in conv2d
data_format='NHWC')
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 670, in convolution
op=op)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 338, in with_space_to_batch
return op(input, num_spatial_dims, padding)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 662, in op
name=name)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 131, in _non_atrous_convolution
name=name)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 399, in conv2d
data_format=data_format, name=name)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2508, in create_op
set_shapes_for_outputs(ret)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1873, in set_shapes_for_outputs
shapes = shape_func(op)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1823, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn
debug_python_shape_fn, require_shape_fn)
File "/Users/schmatz/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 676, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Negative dimension size caused by subtracting 8 from 4 for 'conv2d_1/convolution' (op: 'Conv2D') with input shapes: [?,4,84,84], [8,8,84,32].
Question about clipping
Hi!
Could you please explain why you make error clipping such a way?
`
$ git diff a83c4b3
...
.- # Clip the error term to be between -1 and 1
.- error = y - q_value
.- clipped_error = tf.clip_by_value(error, -1, 1)
.- loss = tf.reduce_mean(tf.square(clipped_error))
.+ # Clip the error, the loss is quadratic when the error is in (-1, 1), and linear outside of that region
.+ error = tf.abs(y - q_value)
.+ quadratic_part = tf.clip_by_value(error, 0.0, 1.0)
.+ linear_part = error - quadratic_part
.+ loss = tf.reduce_mean(0.5 * tf.square(quadratic_part) + linear_part)
`
It seems like good improvement but not like in original paper. What is the benefit?
Thanks!
About mode set for exploration and exploitation
In the mode set up there are three modes:
But it does not do anything different each of the modes. As far as my understanding goes it should take only np.argmax in the exploit mode but I do not think it is doing so.
Please let me know if I am getting this wrong. This is near line 207 - 214.
Thanks
268:processed_observation = np.maximum(observation, last_observation)
what dose this code mean? I'm a little confused
please help ~
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.