ml-agents

1073 提交

337 分支

128 Plastic标签

目录树: a50aadda

作者	SHA1	备注	提交日期
eshvk	cc9bdf17	Added logging per Brain of time to update policy, time elapsed during training, time to collect experiences, buffer length, average return	6 年前
eshvk	fb04c40c	Reorganize to make metrics collection more accurate	6 年前
GitHub	93760bc4	Adds SubprocessUnityEnvironment for parallel envs (#1751 ) This commit adds support for running Unity environments in parallel. An abstract base class was created for UnityEnvironment which a new SubprocessUnityEnvironment inherits from. SubprocessUnityEnvironment communicates through a pipe in order to send commands which will be run in parallel to its workers. A few significant changes needed to be made as a side-effect: * UnityEnvironments are created via a factory method (a closure) rather than being directly created by the main process. * In mlagents-learn "worker-id" has been replaced by "base-port" and "num-envs", and worker_ids are automatically assigned across runs. * BrainInfo objects now convert all fields to numpy arrays or lists to avoid serialization issues.	6 年前

作者

SHA1

备注

提交日期

eshvk

cc9bdf17

Added logging per Brain of time to update policy, time elapsed during training, time to collect experiences, buffer length, average return

6 年前

eshvk

fb04c40c

Reorganize to make metrics collection more accurate

6 年前

GitHub

93760bc4

Adds SubprocessUnityEnvironment for parallel envs (#1751 )

This commit adds support for running Unity environments in parallel.
An abstract base class was created for UnityEnvironment which a new
SubprocessUnityEnvironment inherits from.

SubprocessUnityEnvironment communicates through a pipe in order to
send commands which will be run in parallel to its workers.

A few significant changes needed to be made as a side-effect:
* UnityEnvironments are created via a factory method (a closure)
  rather than being directly created by the main process.
* In mlagents-learn "worker-id" has been replaced by "base-port"
  and "num-envs", and worker_ids are automatically assigned across runs.
* BrainInfo objects now convert all fields to numpy arrays or lists to
  avoid serialization issues.

6 年前

3 次代码提交 (a50aadda-72a0-4ffd-8aab-6622aa659344)