wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-14 11:17:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Also refactor DQN to use shared RLlib models (#730)

Browse Source 
* wip

* works with cartpole

* lint

* fix pg

* comment

* action dist rename

* preprocessor

* fix test

* typo

* fix the action[0] nonsense

* revert

* satisfy the lint

* wip

* works with cartpole

* lint

* fix pg

* comment

* action dist rename

* preprocessor

* fix test

* typo

* fix the action[0] nonsense

* revert

* satisfy the lint

* Minor indentation changes.

* fix merge

* add humanoid

* initial dqn refactor

* remove tfutil

* fix calls

* fix tf errors 1

* closer

* runs now

* lint

* tensorboard graph

* fix linting

* more 4 space

* fix

* fix linT

* more lint

* oops

* es parity

* remove example.py

* fix training bug

* add cartpole demo

* try fixing cartpole

* allow model options, configure cartpole

* debug

* simplify

* no dueling

* avoid out of file handles

* Test dqn in jenkins.

* Minor formatting.

* fix issue

* fix another

* Fix problem in which we log to a directory that hasn't been created.
This commit is contained in:
Eric Liang
2017-07-26 12:29:00 -07:00
committed by Philipp Moritz
parent 8ad9ced99b
commit b6a18cb39b
13 changed files with 399 additions and 1302 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/ray/rllib/models/model.py
+12 -11
View File
@@ -9,20 +9,21 @@ class Model(object):
Models convert input tensors to a number of output features. These features
can then be interpreted by ActionDistribution classes to determine
e.g. agent action values.
The last layer of the network can also be retrieved if the algorithm
needs to further post-processing (e.g. Actor and Critic networks in A3C).
Attributes:
inputs (Tensor): The input placeholder for this model.
outputs (Tensor): The output vector of this model.
last_layer (Tensor): The network layer right before the model output.
"""
def __init__(self, inputs, num_outputs):
def __init__(self, inputs, num_outputs, options):
self.inputs = inputs
self.outputs = self._init(inputs, num_outputs)
self.outputs, self.last_layer = self._init(
inputs, num_outputs, options)
def _init(self):
"""Initializes the model given self.inputs and self.num_outputs."""
"""Builds and returns the output and last layer of the network."""
raise NotImplementedError
def inputs(self):
"""Returns the input placeholder for this model."""
return self.inputs
def outputs(self):
"""Returns the output tensor of this model."""
return self.outputs