d993c549
[Added the unity side code]
6 年前
fad0da30
Log run-id in console
6 年前
e47cec56
[Initial Commit]
6 年前
195ac934
Merge branch 'develop' into develop-runs
# Conflicts:
# python/learn.py
# python/unitytrainers/trainer.py
6 年前
b6fe0bca
Merge pull request #906 from Unity-Technologies/develop-no-discrete-obs
Remove Discrete Observations
6 年前
bee52bce
Additional documentation changes
6 年前
96e599e1
New proto files
6 年前
b46b8708
Rename function
6 年前
ebd9dab4
Update documentation appropriately
6 年前
5e48766d
Remove discrete observations
6 年前
4b3c6c9f
Merge pull request #885 from Unity-Technologies/release-v0.4
Release v0.4
6 年前
bd33996c
Merge branch 'master' into release-v0.4
6 年前
68d6170f
Error message when using ODD and Curiosity ( #883 )
* Remove extra bouncer brain hyperparameters
* Add error when using curiosity+odd
6 年前
dda6ad8b
Replaced message printed in Python and in documentation. ( #881 )
6 年前
f7b35d90
change the visual scenes to default to player brain ( #879 )
6 年前
6df07946
Fix for Discrete observations + Curiosity ( #866 )
6 年前
4c6439d5
[Attempted fix]
6 年前
d73c47c9
removed the internal brain from all the visual scenes, since they've not been trained for them ( #877 )
6 年前
9156737e
Merge pull request #876 from Unity-Technologies/release-windows-save-model-fix
some hack to make windows save the model when do ctrl+c
6 年前
fe2d3fdc
Update document ( #875 )
6 年前
b5722dc9
Fix for visual observation w/ curiosity ( #873 )
6 年前
3990eceb
Fix wall material ( #874 )
6 年前
75218e58
Several final improvement to docs, scene and configs. ( #871 )
* Added missing declaration to docs sample code.
* Added pretrained model as default graph in Internal brain of Tennis scene
* Disabled PlayerBrain in Tennis by default.
* Removed accidental config.
6 年前
3c4cb523
some hack to make windows save the model when do ctrl+c
6 年前
6092b677
Merge pull request #872 from Unity-Technologies/release-v0.4-hallwayil-bugfix
[Hotfix] Remove code in PushAgentBasic that presumes that there is only one brain
6 年前
ce9470dc
[Removed log what lookDir is 0 in Bouncer] ( #861 )
Also made the look code into Update
6 年前
2855c222
Replaced Collision enter with collision stay ( #867 )
6 年前
696c13d2
Fix BananaIL frozen agent material ( #865 )
* Fix BananaIL frozen agent material
* [Fix] Added texture on the imitation learning scene and linked the models to the internal brains
6 年前
2c6089e7
Make ball opaque ( #870 )
6 年前
c0e73bcb
Fix typo ( #864 )
6 年前
2dd658e3
[Hotfix] Remove code in PushAgentBasic that presumes that there is only one brain
6 年前
1d55c571
Fix for “missing” pretrained model ( #862 )
6 年前
cbc2885c
improved the windows doc to make it more user friendly ( #868 )
6 年前
87653e9c
make the doc less confusing, so that people don't read tfsharp repo too much ( #869 )
6 年前
758c611a
fix all the places that used v0.3 and should be fixed, also updated t… ( #863 )
* fix all the places that used v0.3 and should be fixed, also updated the migration doc
* resolved the comment
6 年前
6e6e8d96
Fix for CC models w/ RNN and Curiosity ( #860 )
6 年前
3c84cde2
[Documentation] Added using MLAgents to the Create new Environment page ( #859 )
6 年前
7eebb5f6
Fixes for broken materials ( #855 )
* Fix materials for wall and checker
* Make the ball orange again
6 年前
b22ddd94
Remove old `.meta` file.
6 年前
0217a858
refactored the aws doc ( #848 )
* refactored the aws doc
* some more modification
* resolved the comments
6 年前
47fc38ab
Additional Tests & Bug Fixes ( #854 )
* Add tests and fix for sparse tensor warning
* Rename mock communicator parameter
* Test longer sequences
* Curiosity tests and bug fixes
6 年前
c9c9e147
Revamp Crawler & Walker ( #841 )
* Revamps agent code for walker and crawler environments to use shared JointDriveController system.
* Crawler has been reworked to be very cute.
* Crawler & Walker environments have been reworked to be visually consistent.
* Added Dynamic Crawler scene.
* All scenes re-trained and new models added.
* Documentation changes.
6 年前
a720e370
Fix bug and update tests ( #850 )
6 年前
0f65e272
[Addresses #842 ] ( #849 )
In the case the agent is done imediately after spawning, its stats are empty because the stats need at least 2 successive experieces to create the stats.
By specifying the default value of 0, the error does no longer appear
6 年前
8526dcfc
Fix for visual observations ( #847 )
6 年前
c70122b1
[The first inference setting needs to be read from the batcher before the Engine is configured] ( #844 )
6 年前
282d5bd4
Fix Pytests ( #843 )
6 年前
5d402be9
Minor Optimizations ( #836 )
6 年前
6b1ba14a
Develop axis support ( #829 )
6 年前
e195b495
Merge pull request #838 from Unity-Technologies/develop-bc
[Imitation Learning] Minor fix to make sure that step increment loads from the last saved global step if the model is being trained after loading
6 年前
vincentpierre
Arthur Juliani
GitHub
vincentg
eshvk