Gal Leibovich a1bb8eef89 DDPG Critic Head Bug Fix (#344) ...

* A bug fix for DDPG, where the update to the policy network was based on the sum of the critic's Q predictions on the batch instead of their mean

2019-06-05 17:47:56 +03:00

..

agents

DDPG Critic Head Bug Fix (#344)

2019-06-05 17:47:56 +03:00

architectures

DDPG Critic Head Bug Fix (#344)

2019-06-05 17:47:56 +03:00

dashboard_components

Batch RL (#238)

2019-03-19 18:07:09 +02:00

data_stores

Uploading checkpoint if crd provided (#191)

2019-04-26 12:27:33 -07:00

environments

Enabling Coach Documentation to be run even when environments are not installed (#326)

2019-05-27 10:46:07 +03:00

exploration_policies

Create a dataset using an agent (#306)

2019-05-28 09:34:49 +03:00

filters

applying filters for a csv loaded dataset + some bug-fixes in data loading (#319)

2019-05-28 15:44:55 +03:00

graph_managers

Create a dataset using an agent (#306)

2019-05-28 09:34:49 +03:00

memories

applying filters for a csv loaded dataset + some bug-fixes in data loading (#319)

2019-05-28 15:44:55 +03:00

off_policy_evaluators

Create a dataset using an agent (#306)

2019-05-28 09:34:49 +03:00

orchestrators

Uploading checkpoint if crd provided (#191)

2019-04-26 12:27:33 -07:00

presets

Preset dependent number of csv read attempts in golden testing (#334)

2019-05-28 12:19:57 +03:00

tests

tests: added assert for cp param and changing test args order (#342)

2019-06-05 00:16:50 +03:00

utilities

fix for finding the right filter checkpoint to restore + do not update internal filter state when evaluating + fix SharedRunningStats checkpoint filenames (#147)

2018-12-17 21:36:27 +02:00

__init__.py

pre-release 0.10.0

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

base_parameters.py

Preset dependent number of csv read attempts in golden testing (#334)

2019-05-28 12:19:57 +03:00

checkpoint.py

Implement frame-work agnostic rollout and training workers (#137)

2018-11-23 18:05:44 -08:00

coach.py

Uploading checkpoint if crd provided (#191)

2019-04-26 12:27:33 -07:00

core_types.py

add __truediv__, __rtruediv__ and __eq__ to StepMethod

2019-04-09 12:14:27 -04:00

dashboard.py

fix dashboard to allow connections from a remote machine. (#231)

2019-03-10 13:15:14 +02:00

debug_utils.py

removing datasets + imports optimization

2018-08-27 10:54:11 +03:00

level_manager.py

rename AgentInterface.emulate_observe_on_trainer or observe_transition and call from AgentInterface.observe

2019-04-09 12:14:27 -04:00

logger.py

Batch RL (#238)

2019-03-19 18:07:09 +02:00

plot_atari.py

pre-release 0.10.0

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

renderer.py

muting pygame's hello message (#116)

2018-11-18 18:02:55 +02:00

rollout_worker.py

Uploading checkpoint if crd provided (#191)

2019-04-26 12:27:33 -07:00

run_multiple_seeds.py

Changed run_multiple_seeds to support mxnet. And fix other bugs. (#122)

2018-11-25 08:33:09 +02:00

saver.py

added missing license headers

2018-11-27 22:43:40 +02:00

schedules.py

pre-release 0.10.0

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

spaces.py

Batch RL (#238)

2019-03-19 18:07:09 +02:00

training_worker.py

Uploading checkpoint if crd provided (#191)

2019-04-26 12:27:33 -07:00

utils.py

integration test changes to reach the train part (#254)

2019-03-27 21:14:19 +02:00