a97ffb47
Attempt reward reporting
5 年前
c2b729a6
Fix memory leak
5 年前
9e661f0c
Looks like it's training
5 年前
2c9376bc
Convert to trajectory
5 年前
f008dac0
Use ProcessingBuffer in AgentProcessor
5 年前
34f9577c
Merge branch 'develop' into develop-agentprocessor
5 年前
1e36028d
Runs but doesn't do anything yet
5 年前
17dca3ce
Another nonworking commit
5 年前
02b5e1ef
Revert buffer for now
5 年前
3434352a
Non-working commit
5 年前
73000a6b
Merge branch 'develop' into develop-splitbuffer
5 年前
fd0647a6
Rename append_update_buffer to append_to_update_buffer
5 年前
c2d216ca
Add type hints to Buffer
5 年前
c5b23f46
Remove MANIFEST file
5 年前
a80b47d1
Fix demo loader and remaining tests
5 年前
29cdf77a
Fix RL tests
5 年前
9053610f
Fix buffer tests and truncate
5 年前
e5459c49
buffer split for SAC
5 年前
df5ee7bf
Split buffer into two buffers (PPO works)
5 年前
e6cace92
add options to set version on files ( #2954 )
* add options to set version on files
* fix precommit
5 年前
bc5bf388
Convert most other scenes to RayPerception sensor ( #2916 )
5 年前
e2eef3c4
Clean up env logging on initialization ( #2950 )
5 年前
e2e76c51
Develop barracuda 0.3.x ( #2952 )
* Removed Barracuda as drop-in library, added Barracuda package dependency
* Removed Google Protobuf library as now it comes with Barracuda package
* List<T>.Length seems to be extension, which is not available in .NET coming with Unity 2017, switched to .Count
5 年前
28dbf4c5
Allow --version argument in mlagents-learn ( #2942 )
* allow --version argument in mlagents-learn
* Develop version print add strings (#2945 )
* add __version__ to libs
* more version info
* use actual version
5 年前
5ff3ad8f
Update Learning-Environment-Create-New.md ( #2925 )
Added a missing instruction in the Final Editor Setup section.
5 年前
8a15cac5
Making the behavior type and enum ( #2937 )
* Making the behavior type and enum
* CamelCase
5 年前
e96b80db
recieves brain_name and identifier on python side
5 年前
69d1a033
Develop remove past action communication ( #2913 )
* Modifying the .proto files
* attempt 1 at refactoring Python
* works for ppo hallway
* changing the documentation
* now works with both sac and ppo both training and inference
* Ned to fix the tests
* TODOs :
- Fix the demonstration recorder
- Fix the demonstration loader
- verify the intrinsic reward signals work
- Fix the tests on Python
- Fix the C# tests
* Regenerating the protos
* fix proto typo
* protos and modifying the C# demo recorder
* modified the demo loader
* Demos are loading
* IMPORTANT : THESE ARE THE FILES USED FOR CONVERSION FROM OLD TO NEW FORMAT
* Modified all the demo files
* Fixing all the tests
* fixing ci
* addressing comments
* removing reference to memories in the ll-api
5 年前
c257e053
set team id in prefab
5 年前
38d39e38
disable tensorflow warnings by default ( #2931 )
5 年前
184af227
splitting brain params into brain name and identifiers
5 年前
8426501b
Fix width and height in visual observations ( #2919 )
* swap h/w in sensor
* change texture to non-square, retrain model
* get dimensions from RenderTexture
5 年前
518ce6f8
added team id and identifier concat to behavior parameters
5 年前
99981937
fix errors from new flake8-comprehensions ( #2917 )
5 年前
c0453ae1
Merge pull request #2912 from Unity-Technologies/develop-allbraininfo
Bubbled up indexing of AllBrainInfo to trainer controller from trainers
5 年前
b11f04ea
Fixed test code by creating brain_name variable instead of hardcoding
5 年前
13fe9cf8
Bubbled up indexing of AllBrainInfo to trainer controller from trainers
5 年前
05a54c3b
Ray Perception Sensor docs ( #2911 )
* docs, migration, timers
* add screenshot
* remove added whitespace
5 年前
2e6bab0d
RayPerception sensor ( #2874 )
5 年前
e0339240
add check for merge conflict strings ( #2910 )
5 年前
f57b7ac6
Allow usage with tensorflow 2.0.0 (via tf.compat.v1) ( #2665 )
5 年前
00107b93
Fixing inference for hallway
5 年前
bf68edcf
ingore attribute-defined-outside-init in multi_gpu_policy ( #2876 )
5 年前
e6f549dc
[MLA-12] update protobuf for vector observations ( #2862 )
5 年前
04b456eb
Add model for render texture agent ( #2863 )
5 年前
7f77b7d7
Add ISensor.Update() ( #2852 )
5 年前
3a6ceea4
Migration guide for action/observation changes. ( #2850 )
* Migration guide for action/observation changes.
* remove whitespace
5 年前
ccb7eab4
Remove {text,custom} {action,observations} ( #2839 )
* delete text actions and obs
* delete custom actions and obs
* regenerate protos
* cleanup C#
* format
* fix tests
* fix base env signature
* doc cleanup
5 年前
5e46c984
Fix serialization for m_TrainingConfiguration ( #2826 )
5 年前
e9dd195d
[yamato] Set triggers for any PR against a target branch. ( #2848 )
5 年前
Ervin Teng
GitHub
Chris Elion
Ervin T
Andrew Cohen
Chris Goy