wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-02 13:01:01 +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/catalog.py
+7 -3
View File
@@ -44,23 +44,27 @@ class ModelCatalog(object):
"Unsupported args: {} {}".format(action_space, dist_type))
@staticmethod
def get_model(inputs, num_outputs):
def get_model(inputs, num_outputs, options=None):
"""Returns a suitable model conforming to given input and output specs.
Args:
inputs (Tensor): The input tensor to the model.
num_outputs (int): The size of the output vector of the model.
options (dict): Optional args to pass to the model constructor.
Returns:
model (Model): Neural network model.
"""
if options is None:
options = {}
obs_rank = len(inputs.get_shape()) - 1
if obs_rank > 1:
return VisionNetwork(inputs, num_outputs)
return VisionNetwork(inputs, num_outputs, options)
return FullyConnectedNetwork(inputs, num_outputs)
return FullyConnectedNetwork(inputs, num_outputs, options)
@staticmethod
def get_preprocessor(env_name):