Gal Leibovich 4741b0b916 BCQ variant on top of DDQN (#276) ...

* kNN based model for predicting which actions to drop
* fix for seeds with batch rl

2019-04-16 17:06:23 +03:00

..

embedders

fixes to rainbow dqn + a cartpole based golden test (#253)

2019-03-21 12:57:56 +02:00

heads

BCQ variant on top of DDQN (#276)

2019-04-16 17:06:23 +03:00

middlewares

fixes to rainbow dqn + a cartpole based golden test (#253)

2019-03-21 12:57:56 +02:00

__init__.py

pre-release 0.10.0

2018-08-13 17:11:34 +03:00

architecture.py

bug-fix for l2_regularization not in use (#230)

2019-03-03 15:11:06 +02:00

distributed_tf_utils.py

Removed TF warning when training in a distributed setting (#133)

2018-11-21 16:09:04 +02:00

general_network.py

bug-fix for l2_regularization not in use (#230)

2019-03-03 15:11:06 +02:00

layers.py

fixes to rainbow dqn + a cartpole based golden test (#253)

2019-03-21 12:57:56 +02:00

savers.py

allow serializing from/to arrays/str from GlobalVariableSaver (#285)

2019-04-04 11:09:19 -04:00

shared_variables.py

Fixes for having NumpySharedRunningStats syncing on multi-node (#139)

2018-11-23 16:11:47 +02:00

utils.py

Removed tensorflow specific code in presets (#59)

2018-11-06 17:39:29 +02:00