1aa07606
fix imports for 1.14
5 年前
8da16bdb
move compat functions
5 年前
806c77e4
centralize tensorflow imports
5 年前
43e23941
rough pass at tf2 support, needs cleanup
5 年前
2b02b71b
addressing comments from Marwan
5 年前
a64113ea
rough pass at tf2 support, needs cleanup
5 年前
f5b57675
fixing typos
5 年前
68965c7b
Use a class for camera res, not dict ( #2656 )
5 年前
f93ea1e1
removing broken links
5 年前
f4a2facc
Fix issue which prevented training when code stripping was enabled ( #2662 )
5 年前
cc208c00
resolving conflicts
5 年前
6d7d3c22
[migrating] Update migrating docs to call out gRPC service changes. ( #2654 )
5 年前
336e1c34
Rename k_KApiVersion to k_ApiVersion. ( #2655 )
5 年前
7a178f12
Fixed various typos ( #2652 )
* Add console log section to Bug Report form (#2566 )
* Fixed typos
5 年前
aa7cbaf7
Modified meta_curriculum JSON reading loop to only deal with .json ( #2651 )
* Modified meta_curriculum JSON reading loop
* Switched quote styling
* Removed whitespace
5 年前
4980b904
Cleanup visual obs setup ( #2647 )
* DRY up the setup code
* fstrings
5 年前
d1ebca5c
Merge pull request #2649 from Unity-Technologies/release-0.10.0
Merge Release 0.10.0 back to develop
5 年前
8e931d8d
Merge branch 'develop' into release-0.10.0
5 年前
f5a32c75
Fix visual hallway and visual pushblock brains and scenes. ( #2645 )
5 年前
17b3a805
Fix spelling error in documentation ( #2636 )
5 年前
2f74b3cc
Rename protobuf objects to be suffixed with 'Proto' in python and C#. ( #2646 )
5 年前
aa861bef
Improved SAC hyperparameters for Crawler, Walker ( #2635 )
* Tweak SAC hyperparams
* Make network bigger
* Properly report entropy
* Revert "Properly report entropy"
This reverts commit 383a8d8f1d60ee0ef4ffd87a59aa08d974616d4e.
5 年前
cb144f20
small mypy cleanup ( #2637 )
* small mypy cleanup
* sac cleanup
* types for ppo policy init
5 年前
848b383f
Remove Soccer .nn files ( #2615 )
5 年前
20bf7c42
use [] instead of Dictionary.Add to avoid key exception ( #2629 )
5 年前
af32b443
Update Migrating.md with note about environments ( #2624 )
5 年前
89b1c7a8
Better environment shutdown ( #2620 )
* Wait for env process to exit before killing it
* don't propagate signals, better error logging
* set proc1 to None when done
* comments
5 年前
bf4b277e
Record new demos for new envs ( #2622 )
* Re-record demos for new envs
* Add better Hallway brain
* Remove Banana
5 年前
24250c90
Move gRPC code to its own special place ( #2621 )
- exclude .meta files from mixed line ending checks.
- update CommunicatorObjects directory in CI scripts and Proto generation scripts.
5 年前
5b03b7e0
Update Bouncer learning NN file ( #2614 )
5 年前
b78abd36
[ci] Add protobuf generation check as a CI job. ( #2617 )
5 年前
1e7887cc
Update project version to 2017.4.32 ( #2613 )
5 年前
f7288f5d
[protobuf] Update protobufs with patch from circleci. ( #2618 )
5 年前
6f9a2dfa
Tick version of API and pypi packages to 10 ( #2610 )
* Tick versions for pip packages
* Tick API version to 10
5 年前
28ccd100
make docs agree with code ( #2612 )
5 年前
27326893
Add note about using GPU inference for ResNet ( #2607 )
* Add note about using GPU inference for ResNet
5 年前
bebdb293
ML-Agents Branding & Color Updates ( #2583 )
* new env styles rebased on develop
* added new trained models
* renamed food collector platforms
* reduce training timescale on WallJump from 100 to 10
* uncheck academy control on walljump
* new banner image
* rename banner file
* new example env images
* add foodCollector image
* change Banana to FoodCollector and update image
* change bouncer description to include green cube
* update image
* update gridworld image
* cleanup prefab names and tags
* updated soccer env to reference purple agent instead of red
* remove unused mats
* rename files
* remove more unused tags
* update image
* change platform to agent cube
* update text. change platform to agents head
* cleanup
* cleaned up weird unused meta files
* add new wall jump nn files and rename a prefab
* walker change stacked states from 5 to 1
walker collects physics observations so stacked states are not need...
5 年前
473a8758
Develop yaml json loading errors ( #2601 )
* WIP cleanup loading
* better exceptions for parser errors - refer to online lint tools
* feedback - rename variable
5 年前
3cb1755e
When checking for the compatibility of the expert brain with the policy brain, we will remove the action descriptions from the dictionary of things we need to compare. This is to prevent the case where a user has different descriptions for his actions but still wants to train a brain using expert demonstrations. ( #2517 )
5 年前
097b1b86
removing docker and windows docs
5 年前
02f9ad67
added venv setup documentation for windows
5 年前
30042ef7
fix hang with multiple envs ( #2600 )
5 年前
43c13a35
image decompress timer ( #2596 )
* image decompress timer
* dont lazy load the image
5 年前
149ebd67
Fix crash with VAIL + GAIL ( #2598 )
5 年前
36ed3c16
Fix issue exporting graph with multi-GPU ( #2573 )
Our multi-GPU training had a regression such that freezing the
graph was broken. This change fixes that issue by making a few
changes:
* Removes the top level "tower" variable scope added by multi-GPU
so that the output nodes have correct names
* Removes the use of "freeze_graph" and replaces it with our own similar
functionality.
* Adds the "auto reuse" to network layers which require them
5 年前
d64a01e1
Added option to use environment arguments in learn ( #2594 )
* Added option to use environment arguments in learn
* hook into argparse
* add example to readme
5 年前
82bf38ef
TensorFlowSharp is no more ( #2590 )
* TensorFlowSharp is no more
* Removed old documents
5 年前
0d48a352
Use argparse for arg parsing ( #2586 )
* encapsulate commandline args
* fix tests
* add tests on cmdline parsing
* cleanup
* remove docopt
* simplify --slow
5 年前
11e13518
Merge pull request #2580 from Unity-Technologies/develop-removeUnitySDKlog
Remove UnitySDK.log file
5 年前
e1d93a0e
Allow mypy to reject incomplete defs for mlagents-envs ( #2585 )
This wasn't working before because of several remaining partially defined
function definitions.
5 年前
Chris Elion
Anupam Bhatnagar
GitHub
Ervin T