ml-agents

目录树: 3d25f9d2

作者	SHA1	备注	提交日期
GitHub	c6c01a03	Enable pylint and fix a few things (#2767 ) * enable pylint, disable some messages and fix a few * SAC memories in init	5 年前
GitHub	1934bb75	VectorSensor and StackedSensor (#2813 ) * WIP VectorSensor and StackedSensor * fix a few dumb mistakes * more VectorSensor * remove Update(), add util methods, hook into TensorGenerator * WriteApdater to write to tensors and arrays * write float observations * used circular buffer for stacked obs * cleanup * fix unit tests * docstrings * undo accidental checkins * rider suggestions, add range check * bounds check before writing * undo ProjectVersion.txt change * fix unit tests * unit test for VectorSensor * StackingSensor tests * missing meta file * missing meta file * WriteAdapter tests	5 年前
GitHub	fee8879f	Use image ref instead of tags so we don't need to have different image tags for master/develop. (#2834 )	5 年前
GitHub	35892405	Merge pull request #2832 from Unity-Technologies/develop-merge-release-0.11.0 Merge release-0.11.0 into develop	5 年前
Jonathan Harper	7de4046c	Merge remote-tracking branch 'origin/release-0.11.0' into develop	5 年前
GitHub	6ba6f08c	Merge 0.11.0 to develop (#2825 ) * Update package and communicator versions to 0.11 * Remove pip cache fallback for CircleCI This change removes the caching fallback in the case where dependencies change, since it can cause CI failures when we have incompatible dependencies in the cache. * Limit Tensorflow version for tests to <2.0 * Use stable bokken image. (#2815) * build fixes for 2018+ (#2808) * rename CompressionType enum * fix standalone build test for 2018+ * Add more editor versions for testing. (#2809) * class variable for API verison, fix env tests (#2817) * fixed area prefab agents were pointing to the wrong laser gameObject.	5 年前
GitHub	6f921ec5	Fix vertical offsets for RayPerception3D (#2823 ) * clean up ray perception * adjust offsets * remove dead code	5 年前
Jonathan Harper	bae94a76	Add timeout for communicator exchange When we initially connect to the environment using RPCCommunicator, the connection is polled so we don't hang forever on `.recv()` when the environment wasn't launched or failed. However we don't currently have any similar check for the exchanges mid-training-run. This change applies the same timeout from initialization to each exchange, and extends the default `timeout_wait` to 60 seconds to generally improve the chances we won't have a mismatch between environment launch time and the trainer timeout. Tested on: single-env and multi-env cases. Killed 1 environment process manually and saw that the model was saved appropriately and all processes closed.	5 年前
GitHub	d4e58192	[CI] filter remote links, setup nightly full check (#2811 ) * only check local markdown links * nightly circleci runs	5 年前

109 次代码提交 (3d25f9d2-33cd-4ee8-b0d0-43621242d15c)