From 990410d6b7b3a0cac53bc2d7b1c56b7b7160dda0 Mon Sep 17 00:00:00 2001 From: Ruo-Ping Dong Date: Wed, 7 Oct 2020 18:35:00 -0700 Subject: [PATCH 1/5] update changelog --- com.unity.ml-agents/CHANGELOG.md | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/com.unity.ml-agents/CHANGELOG.md b/com.unity.ml-agents/CHANGELOG.md index fbf65a850d..4ea3f1213d 100755 --- a/com.unity.ml-agents/CHANGELOG.md +++ b/com.unity.ml-agents/CHANGELOG.md @@ -15,24 +15,28 @@ and this project adheres to yaml configuration file. [More information here](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-Configuration-File.md#rnd-intrinsic-reward) ### Minor Changes #### com.unity.ml-agents (C#) - - Stacking for compressed observations is now supported. An addtional setting + - Stacking for compressed observations is now supported. An additional setting option `Observation Stacks` is added in editor to sensor components that support compressed observations. A new class `ISparseChannelSensor` with an additional method `GetCompressedChannelMapping()`is added to generate a mapping of the channels in compressed data to the actual channel after decompression, for the python side to decompress correctly. (#4476) - - Added new visual 3DBall environment. (#4513) + - Added a new visual 3DBall environment. (#4513) #### ml-agents / ml-agents-envs / gym-unity (Python) - The Communication API was changed to 1.2.0 to indicate support for stacked compressed observation. A new entry `compressed_channel_mapping` is added to the proto to handle decompression correctly. Newer versions of the package that wish to make use of this will also need a compatible version of the Python trainers. (#4476) - - In `VisualFoodCollector` scene, a vector flag representing the frozen state of + - In the `VisualFoodCollector` scene, a vector flag representing the frozen state of the agent is added to the input observations in addition to the original first-person camera frame. The scene is able to train with the provided default config file. (#4511) + - Added conversion to string for sampler classes to increase the verbosity of + the curriculum lesson changes. The lesson updates would now output the sampler + stats in addition to the lesson and parameter name to the console. ### Bug Fixes #### com.unity.ml-agents (C#) - - Fixed a bug where accessing the Academy outside of play mode would cause the Academy to get stepped multiple times when in play mode. (#4532) + - Fixed a bug where accessing the Academy outside of play mode would cause the + Academy to get stepped multiple times when in play mode. (#4532) #### ml-agents / ml-agents-envs / gym-unity (Python) From 2e39129c422e44eeacc117129818c6683dd1f37d Mon Sep 17 00:00:00 2001 From: Ruo-Ping Dong Date: Wed, 7 Oct 2020 18:38:57 -0700 Subject: [PATCH 2/5] update changelog before release --- com.unity.ml-agents/CHANGELOG.md | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/com.unity.ml-agents/CHANGELOG.md b/com.unity.ml-agents/CHANGELOG.md index 4ea3f1213d..83201d108f 100755 --- a/com.unity.ml-agents/CHANGELOG.md +++ b/com.unity.ml-agents/CHANGELOG.md @@ -7,6 +7,21 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html). ## [Unreleased] + +### Major Changes +#### com.unity.ml-agents (C#) +#### ml-agents / ml-agents-envs / gym-unity (Python) + +### Minor Changes +#### com.unity.ml-agents (C#) +#### ml-agents / ml-agents-envs / gym-unity (Python) + +### Bug Fixes +#### com.unity.ml-agents (C#) +#### ml-agents / ml-agents-envs / gym-unity (Python) + + +## [1.5.0-preview] - 2020-10-14 ### Major Changes #### com.unity.ml-agents (C#) #### ml-agents / ml-agents-envs / gym-unity (Python) From 21659470e7c4a644dfcf50a3fa1caf1123d49e4a Mon Sep 17 00:00:00 2001 From: "Ruo-Ping (Rachel) Dong" Date: Thu, 8 Oct 2020 12:30:49 -0400 Subject: [PATCH 3/5] Update com.unity.ml-agents/CHANGELOG.md Co-authored-by: Chris Elion --- com.unity.ml-agents/CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/com.unity.ml-agents/CHANGELOG.md b/com.unity.ml-agents/CHANGELOG.md index 83201d108f..621d1ef255 100755 --- a/com.unity.ml-agents/CHANGELOG.md +++ b/com.unity.ml-agents/CHANGELOG.md @@ -47,7 +47,7 @@ and this project adheres to camera frame. The scene is able to train with the provided default config file. (#4511) - Added conversion to string for sampler classes to increase the verbosity of the curriculum lesson changes. The lesson updates would now output the sampler - stats in addition to the lesson and parameter name to the console. + stats in addition to the lesson and parameter name to the console. (#4484) ### Bug Fixes #### com.unity.ml-agents (C#) - Fixed a bug where accessing the Academy outside of play mode would cause the From 2b4561668f258822dae417c4e4dddc2bd8d16a0a Mon Sep 17 00:00:00 2001 From: "Ruo-Ping (Rachel) Dong" Date: Thu, 8 Oct 2020 12:30:55 -0400 Subject: [PATCH 4/5] Update com.unity.ml-agents/CHANGELOG.md Co-authored-by: Chris Elion --- com.unity.ml-agents/CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/com.unity.ml-agents/CHANGELOG.md b/com.unity.ml-agents/CHANGELOG.md index 621d1ef255..a64b058058 100755 --- a/com.unity.ml-agents/CHANGELOG.md +++ b/com.unity.ml-agents/CHANGELOG.md @@ -27,7 +27,7 @@ and this project adheres to #### ml-agents / ml-agents-envs / gym-unity (Python) - Added the Random Network Distillation (RND) intrinsic reward signal to the Pytorch trainers. To use RND, add a `rnd` section to the `reward_signals` section of your - yaml configuration file. [More information here](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-Configuration-File.md#rnd-intrinsic-reward) + yaml configuration file. [More information here](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-Configuration-File.md#rnd-intrinsic-reward) (#4473) ### Minor Changes #### com.unity.ml-agents (C#) - Stacking for compressed observations is now supported. An additional setting From c3b056b06b405e2bdcf5bdf0bcc751e3e5f11fbb Mon Sep 17 00:00:00 2001 From: Ruo-Ping Dong Date: Thu, 8 Oct 2020 10:52:01 -0700 Subject: [PATCH 5/5] add localization PR to changelog --- com.unity.ml-agents/CHANGELOG.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/com.unity.ml-agents/CHANGELOG.md b/com.unity.ml-agents/CHANGELOG.md index 83201d108f..88884ade0f 100755 --- a/com.unity.ml-agents/CHANGELOG.md +++ b/com.unity.ml-agents/CHANGELOG.md @@ -48,6 +48,8 @@ and this project adheres to - Added conversion to string for sampler classes to increase the verbosity of the curriculum lesson changes. The lesson updates would now output the sampler stats in addition to the lesson and parameter name to the console. + - Localized documentation in Russian is added. Thanks to @SergeyMatrosov for + the contribution. (#4529) ### Bug Fixes #### com.unity.ml-agents (C#) - Fixed a bug where accessing the Academy outside of play mode would cause the