Thom Lane 3358e04a6a Corrected MXNet's PPO Head for Continuous Action Spaces (#84) ...

* Changes required for Continuous PPO Head with MXNet. Used in MountainCarContinuous_ClippedPPO.

* Simplified changes for continuous ppo.

* Cleaned up to avoid duplicate code, and simplified covariance creation.

2018-11-15 13:27:54 -08:00

..

agents

Simulating the act on the trainer. (#65)

2018-11-15 08:38:58 -08:00

architectures

Corrected MXNet's PPO Head for Continuous Action Spaces (#84)

2018-11-15 13:27:54 -08:00

dashboard_components

pre-release 0.10.0

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

data_stores

Adding target reward and target sucess (#58)

2018-11-12 15:03:43 -08:00

environments

update of api docstrings across coach and tutorials [WIP] (#91)

2018-11-15 15:00:13 +02:00

exploration_policies

update of api docstrings across coach and tutorials [WIP] (#91)

2018-11-15 15:00:13 +02:00

filters

Simulating the act on the trainer. (#65)

2018-11-15 08:38:58 -08:00

graph_managers

Simulating the act on the trainer. (#65)

2018-11-15 08:38:58 -08:00

memories

Simulating the act on the trainer. (#65)

2018-11-15 08:38:58 -08:00

orchestrators

Adding target reward and target sucess (#58)

2018-11-12 15:03:43 -08:00

presets

Enable distributed SharedRunningStats (#81)

2018-11-13 19:17:38 +02:00

tests

create per environment Dockerfiles. (#70)

2018-11-14 07:40:22 -08:00

traces

trace tests update

2018-10-02 17:55:16 +03:00

utilities

CARLA cleanups + calculating the distance to goal

2018-09-16 16:37:04 +03:00

__init__.py

pre-release 0.10.0

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

base_parameters.py

Simulating the act on the trainer. (#65)

2018-11-15 08:38:58 -08:00

coach.py

Simulating the act on the trainer. (#65)

2018-11-15 08:38:58 -08:00

core_types.py

update of api docstrings across coach and tutorials [WIP] (#91)

2018-11-15 15:00:13 +02:00

dashboard.py

pre-release 0.10.0

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

debug_utils.py

removing datasets + imports optimization

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

level_manager.py

Simulating the act on the trainer. (#65)

2018-11-15 08:38:58 -08:00

logger.py

Modifying ScreenLogger to optionally not output color codes (#56)

2018-11-05 15:25:49 -08:00

plot_atari.py

pre-release 0.10.0

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

renderer.py

pre-release 0.10.0

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

rollout_worker.py

Simulating the act on the trainer. (#65)

2018-11-15 08:38:58 -08:00

run_multiple_seeds.py

bug-fix in local_batch_run_coach and rename to run_multiple_seeds

2018-08-23 14:39:11 +03:00

schedules.py

pre-release 0.10.0

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

spaces.py

update of api docstrings across coach and tutorials [WIP] (#91)

2018-11-15 15:00:13 +02:00

training_worker.py

Simulating the act on the trainer. (#65)

2018-11-15 08:38:58 -08:00

utils.py

Integrate coach.py params with distributed Coach. (#42)

2018-11-05 09:33:30 -08:00