Itai Caspi 11faf19649 QR-DQN bug fix and imporvements (#30) ...

* bug fix - QR-DQN using error instead of abs-error in the quantile huber loss

* improvement - QR-DQN sorting the quantile only once instead of batch_size times

* new feature - adding the Breakout QRDQN preset (verified to achieve good results)

2017-11-29 14:01:59 +02:00

..

__init__.py

coach v0.8.0

2017-10-19 13:10:15 +03:00

architecture.py

bug fix - remove import warning when everything was imported successfully + changed global step api to match TF 1.4

2017-11-06 17:28:13 +02:00

embedders.py

Unify base class using new-style (object).

2017-10-26 12:33:09 +03:00

general_network.py

clean up input embeddings setup

2017-11-14 17:39:18 +02:00

heads.py

QR-DQN bug fix and imporvements (#30)

2017-11-29 14:01:59 +02:00

middleware.py

clean up input embeddings setup

2017-11-14 17:39:18 +02:00

shared_variables.py

Fix std calculation using unbiased estimation in sharing stat mode.

2017-11-07 20:19:54 +02:00