GitHub
c1340b0e
Hotfix docs odd ( #3379 )
* Updating version number (#3366 )
* updating version number
* fixing version numbers
* migration guide (#3375 )
* Reduce num steps for walljump (#3377 )
* Fixing the Docs on On Demand Decision
Co-authored-by: Anupam Bhatnagar <anupambhatnagar@gmail.com>
Co-authored-by: Chris Elion <celion@gmail.com>
Co-authored-by: Ervin T. <ervin@unity3d.com>
5 年前
GitHub
ae9d12b5
Remove monitor ( #3372 )
* Removing the monitor
* Editing the migrating docs
* Readding the Monitor in the examples folder
* Editing the Migrating doc
5 年前
GitHub
d1644496
Remove UpdateAgentAction ( #3373 )
5 年前
GitHub
434985b2
Split out 0.14 in the migration guide ( #3374 )
5 年前
GitHub
44780e39
Add missing backquote in generalized training docs ( #3370 )
5 年前
GitHub
b8bfc79c
set package and API to 0.15.0-dev0 ( #3369 )
5 年前
GitHub
77c3c343
Updating version number ( #3367 )
* updating version number
* fixing version numbers
5 年前
GitHub
03c8559b
Fix migration (Academy.DestroyAction is internal) ( #3364 )
5 年前
GitHub
ad48c521
Fix typos. ( #3363 )
Co-authored-by: Chris Elion <celion@gmail.com>
5 年前
GitHub
0c4d68d1
Exposing the last action in the Agent API ( #3351 )
* Exposing the last action in the Agent API
* INDENTATION makes me \t\t\t mad
* Update Agent.cs
5 年前
GitHub
63959125
backport tf2bc changes from barracuda-release ( #3341 )
5 年前
GitHub
bde6cfaf
Update docs to reflect new package installation workflow. ( #3362 )
- Fix old material name references.
- Update outdated code comments.
5 年前
GitHub
6d26dc53
Link to penguins tutorial. ( #3361 )
5 年前
GitHub
18429825
AddComponentMenu for DecisionRequester ( #3360 )
5 年前
GitHub
ae97ab3a
Soccer refactor ( #3331 )
5 年前
GitHub
4d252428
move Startup ( #3357 )
5 年前
GitHub
3efcefe3
make some more classes and methods internal ( #3353 )
* WIP public->internal
* DemoStore back to public, internal on Timers
5 年前
GitHub
8eb8e279
Fix WallJump yaml indentation in docs and curriculum config ( #3340 )
* Fix yaml indentation in Curriculum Learning docs
* Fix yaml indentation in WallJump curriculum config
5 年前
GitHub
3725e85f
fix academy doc link ( #3349 )
5 年前
GitHub
9b72aab2
Making some fields and properties internal ( #3342 )
* Making some fields and properties internal
* Fixing the formating
* Making more things internal
* Adressing the comments
* reverting the changes made to the recorder
* WriteAdapter public
* Have to make AgentInfo and TensorProxy public because of changes to write adapter and the demorecorder
5 年前
GitHub
6284ea4a
Reduce max steps for Bouncer, summary for Hallway ( #3343 )
5 年前
GitHub
a716c570
Removing general questions and installation/setup template ( #3347 )
* removing general questions and installation/setup template
* Keep links Discussion and Installation
Co-authored-by: Chris Elion <celion@gmail.com>
5 年前
GitHub
3bd57902
fix MissingReferenceException in GridWorld ( #3346 )
5 年前
GitHub
4f71523a
Migration guide for RayPerceptionSensor+scale ( #3344 )
* Migration guide for RayPerceptionSensor+scale
Followup from https://github.com/Unity-Technologies/ml-agents/pull/3334
* whitespace
5 年前
GitHub
b12b906f
Make RayPerception sensor work better with transforms that have scale ( #3334 )
* handle non-1 scale, handle 0 length
* draw scaled spheres correctly, add tests
5 年前
GitHub
7ad624da
testing: exit playback specified number of episodes ( #3332 )
5 年前
GitHub
3afec7c1
Avoid scores and Unity logo overlap ( #3324 )
5 年前
GitHub
9d6c16f0
Update BananaCollector reference in docs ( #3318 )
5 年前
GitHub
7248d2dd
External il2cpp stubs ( #3330 )
* Fix Windows IL2CPP compilation. This does not address the issues with training when IL2CPP is enabled.
Co-authored-by: Jérémy Graziani <AcelisWeaven@users.noreply.github.com>
5 年前
GitHub
3f3916da
Fix italics ( #3327 )
5 年前
GitHub
93fa865e
Update Barracuda to 0.5.0-preview. ( #3329 )
5 年前
GitHub
620fa24a
Track reward for inference ( #3320 )
* WIP
* add reward stats
* const, dont write timers on mobile
5 年前
GitHub
c6e5b23e
Develop return float array ( #3319 )
* Decide Action to return float array
* Removing Debug statement
* Fixing the tests
* Fixing the format
* Renaming some variables
* Better memory allocation
5 年前
GitHub
9e969100
clean up migration notes ( #3313 )
* clean up migration notes
* finish sentence
* Remove obsolete info
5 年前
GitHub
e4394d2f
Run training in yamato for a few steps ( #3244 )
5 年前
GitHub
88ad0eea
remove obsolete param from docstring ( #3317 )
5 年前
GitHub
5c192cb5
BehaviorParameters - accessors for undecorated behavior name ( #3316 )
* BehaviorParameters - accessors for undecorated behavior name
* one fully-qualified is enough
5 年前
GitHub
2db09cef
Model override from commandline ( #3265 )
* WIP model override from commandline
* Agent lazy init, multiple overrides
* MLAgentsExamples namespace
* add model override to 3dball
5 年前
GitHub
fed3efdc
Done After Set Reward ( #3311 )
5 年前
GitHub
6ddcef36
Upgrade to barracuda 0.4.0-preview. ( #3310 )
5 年前
GitHub
2990116f
Fix Walker bug with dirToTarget ( #3309 )
5 年前
GitHub
be0e5635
remove deprecated RayPerceptionMB, legacy codepath: ( #3304 )
5 年前
GitHub
18fc5131
Format code and add .editorconfig to our package. ( #3305 )
5 年前
GitHub
6a0dfc09
link to forums from readme ( #3303 )
5 年前
GitHub
5c83c1c7
Remove runtime test folder. Can re-add it once we have runtime tests. ( #3302 )
5 年前
GitHub
23d0a9d8
Fix barracuda assembly references. ( #3301 )
5 年前
GitHub
01b29cec
Ray perception sensor tests ( #3297 )
* tests WIP
* add test for misses, remove obsolete test
* add filtering test
* cleanup
* 2d default, remove constants test
* use built in tags
* copy old physics settings
* manually sync physics transforms
5 年前
GitHub
5c28f394
Revert back to barracuda 0.3.2-preview. ( #3300 )
5 年前
GitHub
ceebacd6
Convert pyramids to Raycast sensor ( #3299 )
5 年前
GitHub
65dbe0ec
Move processing of steps after reset to advance() ( #3271 )
In the previous PR, steps were processed when the env manager was reset. This was an issue for the very first reset, where we don't actually know which agent groups (and AgentManagers) we needed to send the steps to. These steps were being thrown away.
This PR moves the processing of steps to advance(), so that the initial reset steps are simply processed when the next advance(). This also removes the need for an additional block of code in TrainerController to handle the initial reset.
5 年前