215b35c6
[refactor] Optimize buffer sample_minibatch ( #4508 )
* Optimize buffer sample_minibatch
4 年前
60b76790
Random Network Distillation for Torch ( #4473 )
* initial commit
* works with Pyramids
* added unit tests and a separate config file
* Adding first batch of documentation
* adding in the docs that rnd is only for PyTorch
* adding newline at the end of the config files
* adding some docs
* Code comments
* no normalization of the reward
* Fixing the tests
* [skip ci]
* [skip ci] Make sure RND will only work for Torch by editing the config file
* [skip ci] Additional information in the Documentation
* Remove the _has_updated_once flag
4 年前
4e4ad7b0
Don't run value during policy evaluate, optimized soft update function ( #4501 )
* Don't run value during inference
* Execute critic with LSTM
* Address comments
* Unformat
* Optimized soft update
* Move soft update to model utils
* Add test for soft update
4 年前
b6095151
Execute critic with LSTM
4 年前
1f179527
Do not keep gradients on the q for the v backup ( #4504 )
4 年前
f83f10a2
Merge branch 'master' into develop-policyonly
4 年前
fb177485
Merge pull request #4500 from Unity-Technologies/r7-merge-to-master
[release7] merge release branch back to master
4 年前
7754ad7b
Don't run value during inference
4 年前
b57f1294
Remove obsolete Observation class and ToProto() function ( #4499 )
Remove obsolete Observation class and ToProto() function
4 年前
c54a5dc0
remove meta file
4 年前
933819e3
Add version for mypy-protobuf installation ( #4498 )
Add version for mypy-protobuf installation
4 年前
20e35542
add version for mypy-protobuf installation
4 年前
38e56032
Remove obsolete Observation class and ToProto()
4 年前
fc557903
Develop fix visual torchh export ( #4494 )
* Fixing exporting of ONNX for visual when using threading
* docstring was wrong
4 年前
069f10b9
[Bug fix] Export all branches for discrete control torch ( #4491 )
* Export all branches for discrete control torch
* [skip ci] Changelog edits
* Update ml-agents/mlagents/trainers/torch/networks.py
Co-authored-by: Ruo-Ping (Rachel) Dong <ruoping.dong@unity3d.com>
* Update ml-agents/mlagents/trainers/torch/networks.py
* Fix formatting
Co-authored-by: Ruo-Ping (Rachel) Dong <ruoping.dong@unity3d.com>
4 年前
8a0cb969
Fix visual observations with onnx ( #4475 )
* handle visual observations with onnx
* test tensor resize
4 年前
075b2557
[bug-fix] Set number of threads based on allocated CPU count in Docker containers ( #4471 )
* Set num threads properly for Docker
* Pylint-friendly logic
* Use f.read().rstrip()
* Change function names
4 年前
e08765cb
update versions on master ( #4469 )
4 年前
9ed49f5e
Update changelog before branching for release 7 ( #4468 )
* update changelog before release
* missed section
4 年前
53c13a29
docstrings and cleanup around actuators ( #4467 )
* docstrings and cleanup around actuators
* move ActionSpec property from IActionReceiver to IActuator
4 年前
9d840f22
Increase communicator version for concatenated PNGs. ( #4462 )
4 年前
37d730bf
fix sample code for custom SideChannel ( #4466 )
* fix sample code for custom SideChannel
* update python code too
* changelog
4 年前
88d3705f
Minor doc updates on configuration ( #4452 )
* Added link to training configuration file
Realized this link to the configuration file is not linked on this page
* added clarity on checkpoints saving .nn
Updated doc to include point around saving .nn
* Update docs/Training-Configuration-File.md
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
4 年前
7a012c5b
allow ending the episode for MaxStepsReached ( #4453 )
* allow ending the episode for MaxStepsReached
* changelog
* rename and update docs
4 年前
c334bb80
[docs] Fixed parameter to UnityToGymWrapper on line 34 and 37 ( #4392 )
4 年前
2dc34612
Prevent init normalize on --resume ( #4463 )
Co-authored-by: Ervin T. <ervin@unity3d.com>
4 年前
e2dff28f
don't run pytest on doc or C# changes ( #4454 )
* don't run pytest on doc or C# changes
* also run on test dependency configs
4 年前
e2a6998b
disable email checks on markdown-link-check ( #4461 )
4 年前
bae45836
Fixing issue raised in #4393 ( #4438 )
4 年前
fa30409e
update tests to run on 2019.4 ( #4451 )
4 年前
94c7111e
[feature] Enable default settings for TrainerSettings ( #4448 )
* Enable default settings for TrainerSettings
* Improve comments
* Fix bugs and add tests
* Remove unneccessary changes
* Update docs
* Update changelog
* spelling correction
4 年前
da3b0090
[bug-fix] Adjust MKL and KMP Settings ( #4443 )
* Adjust KMP and interop thread settings
* Don't set affinity, seems to slow down on low-CPU machines
4 年前
8334562a
rebuild hallway walls using primatives ( #4445 )
4 年前
cd83c676
move extensions changelog entries to main changelog ( #4427 )
4 年前
a2420677
ignore forum link in full link check ( #4449 )
4 年前
4393ce78
rerun upm tests for sporadic failures ( #4437 )
4 年前
bf6506fc
[feature] Add small CNN for grids 5x5 and up ( #4434 )
4 年前
6986fb10
use LinearEncoder in curiosity and clean up ( #4444 )
4 年前
676f5f7c
[refactor] Refactor GAIL to use new encoder structure ( #4433 )
Co-authored-by: Ervin Teng <ervin@unity3d.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
4 年前
fcbc47b5
load onnx files for testing ( #4208 )
* load onnx files for testing
* changelog
* update interface
4 年前
fc46ff58
Add Smoothing to CameraFollow script ( #4422 )
* update cam script & add comments
* use fixedDeltaTime in SmoothDamp
4 年前
04032209
[MLA-1306] avoid copying png data ( #4430 )
4 年前
71d1ba68
Set num threads to 1 in Torch ( #4436 )
4 年前
6f534366
Add torch_utils class, auto-detect CUDA availability ( #4403 )
* Add torch_utils
* Use torch from torch_utils
* Add torch to banned modules in CI
* Better import error handling
* Fix flake8 errors
* Address comments
* Move networks to GPU if enabled
* Switch to torch_utils
* More flake8 problems
* Move reward providers to GPU/CPU
* Remove anothere set default tensor
* Fix banned import in test
4 年前
beb5eb30
[bug-fix] Fixes for Torch SAC and tests ( #4408 )
* Fixes for Torch SAC and tests
* FIx recurrent sac test
* Properly update normalization for SAC-continuous
* Fix issue with log ent coef reporting in SAC Torch
4 年前
4e6d46cc
[tests] Add tests for Torch PPO ( #4429 )
4 年前
4e93cb6e
[torch] Restructure PyTorch encoders ( #4421 )
* Move linear encoding to NetworkBody
* moved encoders to processors (#4420 )
* fix bad merge
* Get it running
* Replace mentions of visual_encoders
* Remove output_size property
* Fix tests
* Fix some references
* Revert test_simple_rl
* Fix networks test
* Make curiosity test more accomodating
* Rename total_input_size
* [Bug fix] Fix bug in GAIL gradient penalty (#4425 ) (#4426 )
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
* Up number of steps
* Rename to visual_processors and vector_processors
Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>
Co-authored-by: Andrew Cohen <andrew.cohen@unity3d.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
4 年前
cc10cd82
Worm Ragdoll & Env Updates ( #4413 )
* add worm updates
* add rewman
* cp
* normalize rewards
* only cookie
* try 20M. Add3.5Mnn file
* reduce strength to 3000spring
* facing reward troubleshooting
* Update WormAgent.cs
* troubleshoot nan
* try product of rewards
* train 5M steps
* try end episode on target touch
* fix joint obsv
* use 7M steps
* added nn file for observation joint fix. looks great
* don't end episode
* remove old code
* refactor to patterns used in walker & crawler
* add auto-setup code
* reformat
* use head vel
* remove unneeded observ. update prefabs
* update static scenes
* keeps rolling. added debug. try 5 m/s
* gate the facing reward based on angle tolerance
* added 10ms_angle30rew_nn files
* use fromto rot
* use 7M steps
* add new trained files. cleanup code and prefabs
* use avgvel. add code comments
* remove unused method
* add more comments
* Update Learning-E...
4 年前
4eb47e2f
[docs] Update 'Record Demonstrations' documentation ( #4432 )
* [docs] Update 'Record Demonstrations' documentation
Updates a screenshot and documentation to include the newer `Num Steps To Record` field.
4 年前
582859b6
New Crawler Variable Speed Scenes ( #4382 )
* init
* updating prefabs
* spawn a target
* add brains
* update static prefabs
* enable enhanced determinism
* reset manifest
* add nn files. update to 15M steps
* update prefabs
* increase max speed to 15
* add new local model for 15 speed
* update prefabs
* add configs
* update configs/prefabs
* cleanup
* added final nn models
* add new demos and do more cleanup.
* add meta files
* add RigidbodySensor
* update prefab. about to retrain
* remove body pen
* add fixed crawler & retrained nn file, new demos
* train 10M steps
* Update Crawler Docs
* more prefab cleanup
* add meta files
* Update Project/Assets/ML-Agents/Examples/Crawler/Scripts/CrawlerAgent.cs
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
* remove unused prefab
* update comment
* add summary tags
* cleanup and add more comments
* remove unused prefab
* Update P...
4 年前
GitHub
Ervin Teng
Ruo-Ping Dong