19df3524
Fixed typo
6 年前
8956b6d5
More semantically correct description
I feel the previous description was misleading.
6 年前
45a86c85
Merge pull request #1264 from Unity-Technologies/hotfix-050a
Hotfix 050a
6 年前
d2c320dd
Remove graph scope ( #1205 )
* initial commit : Only works with PPO balance ball
* Fix for recurrent
* [Fix indentation error]
* Fixed BC
* Remove Dead code
* Addressing comment : Removing dead code
* Fixing the Pytest
* edited comments
* Removing GraphScope from the InternalBrain (#1227 )
* Documentation changes for removing graph scope (#1226 )
* Documentation changes
* removed the keep checkpoint printing
6 年前
560f1bd7
Merge pull request #1224 from Unity-Technologies/release-v0.5
Release v0.5
6 年前
b97ad521
Release citation ( #1201 )
6 年前
020d6e8b
Fixing tables in documentation and other markdown errors. ( #1199 )
6 年前
50228570
updated the walljump model for the multi-discrete action space ( #1198 )
6 年前
a884806b
Update readmes to be more informative ( #1194 )
* Update readmes to be more informative
* Line lengths
* Address comments
6 年前
af7de3ca
Fix bug when academy max steps is set to nonzero value. ( #1195 )
6 年前
4a881354
fix the training doc ( #1193 )
6 年前
2af80543
Add fix for multiple instances on a single GPU ( #1192 )
6 年前
84a8f112
last bit of doc review from checklist ( #1191 )
* minor grammatical fix
* fixed definition in table
6 年前
a5ab8653
Minor fixes to Gym Link and Feature List ( #1189 )
* broken link for gym
* added gym into feature list
* fixed typo
6 年前
eb2fa490
Update Learning-Environment-Examples.md ( #1188 )
6 年前
63062b92
updated the Pyramids model ( #1184 )
* updated the Pyramids model
* updated the pyramids model, chnaged the max_steps to reflect the new max steps required to achive ~1.8 cumulative reward
6 年前
2ece0b2e
Three Re-trained Models ( #1183 )
* Use new Soccer model
* Use new basic model
* New PushBlock model
* Address comments
6 年前
d203cb30
Ignore envs folder ( #1182 )
6 年前
e952dedf
updated the tfsharp links ( #1181 )
6 年前
a54714f8
Update API to version 5 ( #1179 )
6 年前
5545a22d
Release tf#android fix ( #1180 )
* The Android fix
* additional documentation
* added #
6 年前
ab6eb8dc
Fix TF Nan bug ( #1178 )
* Fix for TF NaNs
* New soccer model
6 年前
24796cf6
Project Version 2017.4 ( #1173 )
* Make project version 2017.4
* updated the documentation
* added the upgrade notes for 2017.1 to 2017.4
* removed the .10f1
* fix the typo and make the language nicer
* resolved the comments
* Wrapping lines.
* Wording.
* resolved part of jeff's comment
* resolved part of jeff's comment
* fixed the link
* Update FAQ.md
Missing "an".
* Missing "an".
6 年前
6b04b516
Consistent string style in trainer_controller.py ( #1177 )
* Consistent string style in trainer_controller.py.
* Linting error in doc.
6 年前
6aa78593
Moving UnitySDK README to correct location, fixing file permissions. ( #1175 )
6 年前
2cd8e250
Documentation 0.5 Release Check List (Part 1) ( #1154 )
6 年前
29084e77
Curriculum learning reward thresholding bug fix ( #1141 )
6 年前
ffffe131
Renamed MLAgentsSDK to UnitySDK. ( #1170 )
6 年前
2f8ad858
Update Getting-Started-with-Balance-Ball.md ( #1168 )
Fix typos
6 年前
fb248d55
.gitignor *.xml is breaks MarathonEnvs
6 年前
f8df71a0
Revert "Release v0.5 (Develop) ( #1203 )" ( #1222 )
This reverts commit 448aac65dc891bad04a23a02d275f6a1d2704e1e.
6 年前
10d2a19d
Release v0.5 (Develop) ( #1203 )
6 年前
a6f45b76
Fixing learn.py, trainer_controller.py, and Docker ( #1164 )
* Fixing learn.py, trainer_controller.py, and Docker
- learn.py has been moved under trainers.
- this was a two line change
- learn.py will no longer be run as a main method
- docopt arguments are strings by default. learn.py now uses
this assumption to correctly parse arguments.
- trainer_controller.py now considers the Docker volume when
accepting a trainer config file path.
- the Docker container now uses mlagents-learn.
* Removing extraneous unity-volume ref.
6 年前
b07dbd66
Adding specific mlagents-learn vs. learn.py example. ( #1157 )
* Adding specific mlagents-learn vs. learn.py example.
* Specifying where to run mlagents-learn in Migrating.md.
6 年前
3c7dc2a1
Release v0.5 gridworld tfmodels ( #1163 )
* Updating re-trained GridWorld models
* Modifying GridWorld scene to link to new models
* Minor tweak to brain type —> Player for GridWorld
6 年前
8eedc76f
[Basic] Added models, fixed Player scene and corebrain internal ( #1156 )
6 年前
2d4b4209
Use single scope declaration for models ( #1160 )
6 年前
6430fc86
Changing learn.py log messages. ( #1159 )
* Changing learn.py log messages.
- learn.py refers to the mlagents-learn script now.
- If a non-existant trainer config is passed, the log message
correctly points that out now.
* Changing the curriculum arg from file to dir.
6 年前
ab0e05b2
fixed the aws doc ( #1158 )
* fixed the aws doc
* remove the cd instruction
6 年前
a69ec095
improve the migration doc ( #1155 )
* improve the migration doc
* fix typo
* resolved all the issues
* resolve the comment
6 年前
2d767f3f
GridWorld now uses action masking ( #1125 )
* GridWorld now uses action masking
* Addressed the comments
* addressed comments
* Added checkbox to turn action masking on/off (#1146 )
* Added checkbox to turn action masking on/off
* Fix to handle the no-action option
* Added comment to GridWorld mentioning the use of action masking. (#1153 )
6 年前
423a6bc9
Replacing training screenshots with updated markdown. ( #1152 )
* Replacing training screenshots with updated markdown.
* Changing bash prompt to be simpler.
6 年前
ab5c49e8
Release v0.5 delete unityagents ( #1151 )
* fixed the loggers
* Modified the documentation
6 年前
bc20a6af
Added the Hallway Model ( #1148 )
6 年前
a94b7308
Fixed the gym_unity tests ( #1150 )
6 年前
52958d1e
Fixed the gym_unity tests ( #1149 )
6 年前
bb135f4f
Python version is now restricted to 3.5 or 3.6. ( #1145 )
* Only Python 3.6, bumping package version.
6 年前
108e770e
Updating the migrating doc ( #1137 )
6 年前
fbf92810
Refactor Trainers to use Policy ( #1098 )
6 年前
a53beb42
Downgrade to 2017.1 ( #1133 )
* Downgrade to 2017.1
* Fix MACOSX built executable training
6 年前
GitHub
Arthur Juliani
Vincent(Yuan) Gao
Marwan Mattar