- updated release tag validation script to automate the updating of files with release tags that need to be changed as part of the pre-commit operation.
* Add CreateActuators method to the ActuatorComponent class which wraps the original method. The original method will be removed in the future.
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
- Actuators can now optionally implement IHeuristicProvider to generate heuristic actions for agents.
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Remove extra period
* Update changelog
* Re add a period (#4676)
* Adding a trailing period
* formating
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
* Remove extra period
* Update changelog
* Re add a period (#4676)
* Adding a trailing period
* formating
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
* use int64 steps
* check for NaN actions
Co-authored-by: Ruo-Ping Dong <ruoping.dong@unity3d.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Torch setup.py
* Set torch to default
* Make torch default in setup.py
* Remove indents
* Remove other instances of TF being used
* Add tensorboard to setup.py
* Adding correst setup commands for verifying torch is installed (#4524)
* Adding correst setup commands for verifying torch is installed
* Editing the test_requirments to add tf and remove torch
* Develop torchdefault raise outside setup (#4530)
* Torch not imported error to raise at first usage
* Torch not imported error to raise at first usage
* [refactor] Use PyTorch TensorBoard utils (#4518)
* Convert stats writer to use PyTorch TB support
* Use common function to print params
* Update test
* Bump tensorboard to 1.15 to fix the tests
* putting tensorboard 1.15.0 as min version requirement
Co-authored-by: vincentpierre <vincentpierre@unity3d.com>
* [Docs] Initial documentation changes for making Torch the default (#4561)
* Initial commit
* Forgotten doc
* Removing the `Installation-Anaconda-Windows.md` as it is deprecated
* Readding the depreacted Installation-Anaconda-Windows.md but leaving it unchanged
* more references to tensorflow removed
* Update README.md
Co-authored-by: Ervin T. <ervin@unity3d.com>
* Change references to .nn to .onnx in docs (#4583)
Co-authored-by: Ervin T. <ervin@unity3d.com>
* [refactor] Add --tensorflow, enable Torch as default setting (#4582)
* Add --tensorflow option
* Switch framework to Pytorch default
* Update changelog
* Re-add --torch
* Edit warning
* Modify Yamato tests (#4584)
* Don't check for PB file in Yamato inference
* Only run inference on ONNX
* Update docs/Unity-Inference-Engine.md with correct tf2onnx versions
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Add reward signal class comments
* More descriptive import of is_available
* Updated installation instructions for PyTorch
* More reward signal comments
* More Windows instructions
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Destroy stepper when playmode change
* Detroy stepper if it does not belong to the current Academy
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
VisualFoodCollector is now an example environment of using a mix of visual and vector observation and is able to train with default config file.
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Added stacking to multi-dimensional and compressed observations and added compressed channel mapping in communicator to support decompression.
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* 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
* Begin porting work
* Add ResNet and distributions
* Dynamically construct actor and critic
* Initial optimizer port
* Refactoring policy and optimizer
* Resolving a few bugs
* Share more code between tf and torch policies
* Slightly closer to running model
* Training runs, but doesn’t actually work
* Fix a couple additional bugs
* Add conditional sigma for distribution
* Fix normalization
* Support discrete actions as well
* Continuous and discrete now train
* Mulkti-discrete now working
* Visual observations now train as well
* GRU in-progress and dynamic cnns
* Fix for memories
* Remove unused arg
* Combine actor and critic classes. Initial export.
* Support tf and pytorch alongside one another
* Prepare model for onnx export
* Use LSTM and fix a few merge errors
* Fix bug in probs calculation
* Optimize np -> tensor operations
* Time action sample function
* Small performance improvement during inference
* ONNX exporting
* Fix some issues with pdf
* Fix bug in pdf function
* Fix ResNet
* Remove double setting
* Fix for discrete actions (#4181)
* Fix discrete actions and GridWorld
* Remove print statement
* Convert List[np.ndarray] to np.ndarray before using torch.as_tensor (#4183)
Big speedup in visual obs
* Develop add fire exp framework (#4213)
* Experiment branch for comparing torch
* Updates and merging ervin changes
* improvements on experiment_torch.py
* Better printing of results
* preliminary gpu experiment
* Testing gpu
* Prepare to see a lot of commits, because I like my IDE and I am testing on a server and I am using git to sync the two
* Prepare to see a lot of commits, because I like my IDE and I am testing on a server and I am using git to sync the two
* _
* _
* _
* _
* _
* _
* _
* _
* Attempt at gpu on tf. Does not work
* _
* _
* _
* _
* _
* _
* _
* _
* _
* _
* _
* Fixing learn.py
* reformating experiment_torch.py
* Pytorch port of SAC (#4219)
* Update add-fire to latest master, including Policy refactor (#4263)
* Update Dockerfile
* Separate send environment data from reset (#4128)
* Fixed a typo on ML-Agents-Overview.md (#4130)
Fixed redundant "to" word from the sentence since it is probably a typo in document.
* Updated the badge’s link to point to the newest doc version
* Replaced all of the doc to release_3_doc
* Fix 3DBall and 3DBallHard SAC regressions (#4132)
* Move memory validation to settings
* Update docs
* Add settings test
* Update to release_3 in installation.md (#4144)
* rename to SideChannelManager +backcompat (#4137)
* Remove comment about logo with --help (#4148)
* [bugfix] Make FoodCollector heuristic playable (#4147)
* Make FoodCollector heuristic playable
* Update changelog
* script to check for old release links and references (#4153)
* Remove package validation suite from Project (#4146)
* RayPerceptionSensor: handle empty and invalid tags (#4155)
* handle empty and invalid tags
* don't compare null or empty tags
* changelog
* avoid console spam when editing tag name
* [docs] Fix a typo in a link in the package docs (#4161)
* update FAQ to include disabling graphics (#4159)
* update FAQ and exception message
* remove colab link
* [MLA-1009] observable performance tests (#4031)
* WIP perf tests
* WIP perf test
* add marker tests too
* move to devproject
* yamato first pass
* chmod
* fix trigger, fix meta files
* fix utr command
* fix artifact paths
* Update com.unity.ml-agents-performance.yml
* test properties, reduce some noise
* timer around RequestDecision
* actually set ObservableAttributeHandling
* undo asmdef changes
* Yamato inference tests (#4066)
* better errors for missing constants
* run inference in yamato after training
* add extension
* debug subprocess args
* fix exe path
* search for executable
* fix dumb bug
* -batchmode
* fail if inference fails
* install tf2onnx on yamato
* allow onnx for overrides (expect to fail now)
* enable logs
* fix commandline arg
* catch exception from SetModel and exit
* cleanup error message
* model artifacts, logs as artifacts, fix pip
* don't run onnx
* cleanup and comment
* update extension handling
* Update CONTRIBUTING.md (#4170)
we removed contributions welcome.
* FoodCollectorAgent - don't convert bool to int (#4169)
* [docs] Corrected num_layers default value (#4167)
* [docs] Fix table formatting (#4168)
* [CI] Better hyperparameters for Pyramids-SAC, WalkerStatic-SAC, and Reacher-PPO (#4154)
* [bug-fix] Initialize-from being incorrectly loaded as "None" rather than None (#4175)
* Modified the documentation of the Heuristic method (default action = previous action) (#4174)
* Modifying the documentation to explain that Heuristic method default action will be the previous action decided by the heuristic. Changing this behavior would be a breking change.
* Rephrase the working of the documentation of the default action of the Heuristic method
* Forgot an import
* [MLA-240] Physic-based pose generation (#4166)
* hierarchy POC
* WIP
* abstract class
* clean up init
* separate files
* cleanup, unit test
* add Articulation util
* sensor WIP
* ArticulationBody sensor, starting docs
* docstrings, cleanup
* hierarchy tests, transform operators
* unit tests
* use Pose struct instead
* delete QTTransform
* rename
* renames and compile fixes
* remove ArticulationBodySensor* for now
* revert CrawlerAgent changes
* rename
* Add TargetController/OrientationCubeController Components & Bugfix (#4157)
* added Target and OCube controllers. updated crawler envs
* update walker prefab
* add refs to prefab
* Update Crawler.prefab
* update platform, ragdoll, ocube prefabs
* reformat file
* reformat files
* fix behavior name
* add final retrained crawler and walker nn files
* collect hip ocube rot in world space
* update crawler observations and update prefabs
* change to 20M steps
* update crwl prefab to 142 observ
* update obsvs to 241. add expvel reward
* change walkspeed to 3
* add new crawler and walker nn files
* adjust rewards
* enable other pairs
* add RewardManager
* cleanup about to do final training
* cleanup add nn files for increased facing rew reduced height rew
* try no facing rew
* add vel only policy, try dy target
* inc torq on cube
* added dynamic cube nn. gonna try 40M steps
* add 40M step test, more cleanup
* change back to 20M steps
* Update WalkerStatic.unity
* add no vel pen nn file
* .005 head height rew
* remove extra walker in scene
* Update WalkerWithTargetPair.prefab
* Update WalkerStatic.unity
* more cleanup add new nn file with less head height reward
* added Target and OCube controllers. updated crawler envs
* update walker prefab
* add refs to prefab
* Update Crawler.prefab
* update platform, ragdoll, ocube prefabs
* reformat file
* reformat files
* fix behavior name
* add final retrained crawler and walker nn files
* collect hip ocube rot in world space
* update crawler observations and update prefabs
* change to 20M steps
* update crwl prefab to 142 observ
* update obsvs to 241. add expvel reward
* change walkspeed to 3
* add new crawler and walker nn files
* adjust rewards
* enable other pairs
* add RewardManager
* cleanup about to do final training
* cleanup add nn files for increased facing rew reduced height rew
* try no facing rew
* add vel only policy, try dy target
* inc torq on cube
* added dynamic cube nn. gonna try 40M steps
* add 40M step test, more cleanup
* change back to 20M steps
* Update WalkerStatic.unity
* add no vel pen nn file
* .005 head height rew
* remove extra walker in scene
* Update WalkerWithTargetPair.prefab
* Update WalkerStatic.unity
* more cleanup add new nn file with less head height reward
* cleanup
* remove comment
* more cleanup
* correct format
* Update ProjectVersion.txt
* change to Log()
* cleanup
* use the starting y position instead of a hard coded height
* test old fromtorot
* add 236 model
* testing new 236 nn files
* add final walker nn files
* cleanup
* crawler cleanup
* update crawler observ size
* add final crawler nn files
* fixed formatting ssues
* [refactor] Remove BrainParameters from Python code (#4138)
* Fix extension package tests (#4189)
* Move Heuristic fixes to changelog bug section (#4177)
* Fix a typo in Python-API.md (#4179)
Fix behavior_spec to behavior_specs
* Docs: note about required Windows Python x86-64 (#4060)
* note about required Windows Python x86-64
Co-authored-by: Arthur Juliani <awjuliani@gmail.com>
Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>
* documentation touchups (#4099)
* doc updates
getting started page now uses consistent run-id
re-order create-new docs to have less back/forth between unity and text editor
* add link explaining decisions where we tell the reader to modify its parameter
* Fix 3DBall PPO hard regression (#4133)
* enforce warnings-as-errors, fix warning (#4191)
* (case 1255312) Conditionally use different namespace for ScriptedImporters (#4188)
* (case 1255312) Conditionally use different namespace for ScriptedImporters.
* Add semi-colon.
* Update barracuda dependency.
* Update changelog.
* Fix PR number.
* Refactor of Curriculum and parameter sampling (#4160)
* Introduced the Constant Parameter Sampler that will be useful later as samplers and floats can be used interchangeably
* Refactored the settings.py to refect the new format of the config.yaml
* First working version
* Added the unit tests
* Update to Upgrade for Updates
* fixing the tests
* Upgraded the config files
* Fixes
* Additional error catching
* addressing some comments
* Making the code nicer with cattr
* Added and registered an unstructure hook for PrameterRandomization
* Updating C# Walljump
* Adding comments
* Add test for settings export (#4164)
* Add test for settings export
* Update ml-agents/mlagents/trainers/tests/test_settings.py
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
* Including environment parameters for the test for settings export
* First documentation update
* Fixing a link
* Updating changelog and migrating
* adding some more tests for the conversion script
* fixing bugs and using samplers in the walljump curriculum
* Changing the format of the curriculum file as per discussion
* Addressing comments
* Update ml-agents/mlagents/trainers/settings.py
Co-authored-by: Ervin T. <ervin@unity3d.com>
* Update docs/Migrating.md
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* addressing comments
Co-authored-by: Ervin T <ervin@unity3d.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* [bug-fix] Make StatsReporter thread-safe (#4201)
* Update changelog for release 4 (#4202)
* don't allow --num-envs >1 with no --env (#4203)
* don't allow --num-envs >1 with no --env
* changelog
* PR feedback
* Add warning if behavior name not found in trainer config (#4204)
Co-authored-by: Ervin T. <ervin@unity3d.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* better logging for NaN rewards (#4205)
* [MLA-1145] don't allow --num-envs >1 with no --env (#4209)
* don't allow --num-envs >1 with no --env (#4203)
* Convert checkpoints to .NN (#4127)
This change adds an export to .nn for each checkpoint generated by
RLTrainer and adds a NNCheckpointManager to track the generated
checkpoints and final model in training_status.json.
Co-authored-by: Jonathan Harper <jharper+moar@unity3d.com>
* Update version for release 4 (master) (#4207)
* Update version for release 4
* newline in json file
* actually fix newline
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Update version for release 4 (release branch) (#4210)
* Update versions for release 4
* Link validation file should ignore itself
* Remove 'unreleased' section from changelog
* Change to 0.18.0 for python versions
* also update extensions package version
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* [MLA-1141] Rigidbody and ArticulationBody sensors (#4192)
* Update release table (#4221)
* Add macOS Catalina notice to FAQ (#4222)
* Add macOS Catalina notice to FAQ
* Change wording and line breaks.
* update com.unity.ml-agents.extensions to Apache 2.0 license (#4223)
* update com.unity.ml-agents.extensions to Apache 2.0 license (#4223) (#4225)
* Throw if Academy.EnvironmentStep() is called recursively (#4227)
* speed up infinite loops
* changelog
* fix job deps (#4230)
* use old yamato test config (#4231)
* Run all package test types (#4232)
* Revert "use old yamato test config" (#4233)
* Revert "use old yamato test config (#4231)"
This reverts commit e5e21dcc2a.
* Apply changes from #4232
* update document (#4237)
small fix to documentation formatting
* Update changelog for .nn checkpoints (#4240)
Co-authored-by: sankalp04 <30798796+sankalp04@users.noreply.github.com>
* Don't drop multiple stats from the same step (#4236)
* add pyupgrade to pre-commit and run (#4239)
* [MLA-427] make pyupgrade convert f-strings too (#4244)
* make pyupgrade convert f-strings too
* Run coverage checks with python3 (#4245)
* Run code coverage for extensions package (#4243)
* run code coverage for extensions package
* reasonable coverage pct
* fix artifactory url (#4246)
* Refactor TFPolicy and Policy
* don't try/except for control flow (#4251)
* Update two docstring references to NNPolicy
* Longer demos for ragdoll envs (#4247)
* [docs] buffer_size parameter clarification (#4252)
* [docs] buffer_size parameter clarification
It was not fully clear that it has a different behavior for PPO and SAC. The docs update should improve the understanding.
* [docs] updated buffer_size parameter clarification
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
* Remove un-needed check
* Remove irrelevant tests
* Address feedback
* [MLA-1172] Reduce calls to training_behaviors (#4259)
* Remove unnecessary line (#4260)
* [MLA-1138] joint observations (#4224)
* Update to latest master
* Refactor TFPolicy and Policy (#4254)
* Refactor TFPolicy and Policy
* Move TF-specific files to tf/ folder
* Move EncoderType and ScheduleType to settings.py
* Move Torch files to separate folder
* Update imports to keep Torch working
* [bugfix] summary writer no longer crashes if Hyperparameters could not be written (#4265)
* Bug fix, returnning an empty string in case of error breaks the summary writter
* addressing comments
* [refactor] Move TF-specific files to tf/ folder (#4266)
* Break up models.py into separate files
* Use network_settings for configuring networks
* [refactor] Make classes except Optimizer framework agnostic (#4268)
* Fixing tensorboard command line params (#4262)
* Update Using-Tensorboard.md
"--logdir=results" is broken in newer versions of tensor board; "logdir results" without the equal sign works. See https://github.com/tensorflow/tensorboard/issues/686
* Removing equal sign from tensorboard command line params in docs
Co-authored-by: Nancy Iskander <nancyiskanderonline@gmail.com>
Co-authored-by: Pulkit Midha <midhapulkit28@gmail.com>
Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>
Co-authored-by: Furkan Çelik <game.wive@gmail.com>
Co-authored-by: Yuan Gao <xiaomaogy88@gmail.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
Co-authored-by: Anupam Bhatnagar <anupam@unity3d.com>
Co-authored-by: Jeffrey Shih <34355042+unityjeffrey@users.noreply.github.com>
Co-authored-by: Christian Coenen <coenen.christian@outlook.com>
Co-authored-by: Florian Pöhler <info@poehler.it>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Hunter-Unity <hunter@unity3d.com>
Co-authored-by: yongjun823 <diddydwns135@gmail.com>
Co-authored-by: Stefano Cecere <stefano.cecere@krur.com>
Co-authored-by: Arthur Juliani <awjuliani@gmail.com>
Co-authored-by: Tom Thompson <208435+codethulu@users.noreply.github.com>
Co-authored-by: Chris Goy <christopherg@unity3d.com>
Co-authored-by: sankalp04 <30798796+sankalp04@users.noreply.github.com>
Co-authored-by: Jonathan Harper <jharper+moar@unity3d.com>
Co-authored-by: Ruo-Ping (Rachel) Dong <dongruoping@gmail.com>
Co-authored-by: Nancy Iskander <n2iskand@uwaterloo.ca>
Co-authored-by: Nancy Iskander <nancyiskanderonline@gmail.com>
* [refactor] Refactor normalizers and encoders (#4275)
* Refactor normalizers and encoders
* Unify Critic and ValueNetwork
* Rename ActionVectorEncoder
* Update docstring of create_encoders
* Add docstring to UnnormalizedInputEncoder
* fix onnx save path and output_name
* add Saver class (only TF working)
* fix pytorch checkpointing. add tensors in Normalizer as parameter
* remove print
* move tf and add torch model serialization
* remove
* remove unused
* add sac checkpoint
* small improvements
* small improvements
* remove print
* move checkpoint_path logic to saver
* [refactor] Refactor Actor and Critic classes (#4287)
* fix onnx input
* fix formatting and test
* [bug-fix] Fix non-LSTM SeparateActorCritic (#4306)
* small improvements
* small improvement
* [bug-fix] Fix error with discrete probs (#4309)
* [tests] Add tests for core PyTorch files (#4292)
* [feature] Fix TF tests, add --torch CLI option, allow run TF without torch installed (#4305)
* Test fixes on add-fire (#4317)
* fix tests
* Add components directory and init (#4320)
* [add-fire] Halve Gaussian entropy (#4319)
* Halve entropy
* Fix utils test
* [add-fire] Add learning rate and beta/epsilon decay to PyTorch (#4318)
* Added Reward Providers for Torch (#4280)
* Added Reward Providers for Torch
* Use NetworkBody to encode state in the reward providers
* Integrating the reward prodiders with ppo and torch
* work in progress, integration with PPO. Not training properly Pyramids at the moment
* Integration in PPO
* Removing duplicate file
* Gail and Curiosity working
* addressing comments
* Enfore float32 for tests
* enfore np.float32 in buffer
* Fix discrete export (#4322)
Fix discrete export
* [add-fire] Fix CategoricalDistInstance test and replace `range` with `arange` (#4327)
* Develop add fire layers (#4321)
* Layer initialization + swish as a layer
* integrating with the existing layers
* fixing tests
* setting the seed for a test
* Using swish and fixing tests
* fixing typo
* [add-fire] Merge post-0.19.0 master into add-fire (#4328)
* Revert "[add-fire] Merge post-0.19.0 master into add-fire (#4328)" (#4330)
This reverts commit 9913e71b6f.
* More comments and Made ResNetBlock (#4329)
* update saver interface and add tests
* update
* Fixed the reporting of the discriminator loss (#4348)
* Fixed the reporting of the discriminator loss
* Update ml-agents/mlagents/trainers/torch/components/reward_providers/gail_reward_provider.py
* fixing pre-commit test
* Fix ONNX import for continuous
* fix export input names
* Behavioral Cloning Pytorch (#4293)
* fix export input name
* [add-fire] Add LSTM to SAC, LSTM fixes and initializations (#4324)
* add comments
* fix bc tests
* change brain_name to behavior_name
* reverting Project settings
* [add-fire] Fix masked mean for 2d tensors (#4364)
* Removing the experiment script from add fire (#4373)
* Removing the experiment script
* Removing the script
* [add-fire] Add tests and fix issues with Policy (#4372)
* Pytorch ghost trainer (#4370)
* add test_simple_rl tests to torch
* revert tests
* Fix of the test for multi visual input
* Make reset block submodule
* fix export input_name
* [add-fire] Memory class abstraction (#4375)
* make visual input channel first for export
* Don't use torch.split in LSTM
* Add fire to test_simple_rl.py (#4378)
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Ervin T <ervin@unity3d.com>
* reverting unity_to_external_pb2_grpc.py
* remove duplicate of curr documentation
* Revert "remove duplicate of curr documentation"
This reverts commit 3d7b809c1e.
* remove duplicated curriculum doc (#4386)
* Fixed discrete models
* Always export one Action tensor (#4388)
* [add-fire] Revert unneeded changes back to master (#4389)
* add comment
* fix test
* add fire clean up docstrings in create policies (#4391)
* [add-fire] Update changelog (#4397)
Co-authored-by: Arthur Juliani <awjuliani@gmail.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Pulkit Midha <midhapulkit28@gmail.com>
Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>
Co-authored-by: Furkan Çelik <game.wive@gmail.com>
Co-authored-by: Yuan Gao <xiaomaogy88@gmail.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
Co-authored-by: Anupam Bhatnagar <anupam@unity3d.com>
Co-authored-by: Jeffrey Shih <34355042+unityjeffrey@users.noreply.github.com>
Co-authored-by: Christian Coenen <coenen.christian@outlook.com>
Co-authored-by: Florian Pöhler <info@poehler.it>
Co-authored-by: Hunter-Unity <hunter@unity3d.com>
Co-authored-by: yongjun823 <diddydwns135@gmail.com>
Co-authored-by: Stefano Cecere <stefano.cecere@krur.com>
Co-authored-by: Tom Thompson <208435+codethulu@users.noreply.github.com>
Co-authored-by: Chris Goy <christopherg@unity3d.com>
Co-authored-by: sankalp04 <30798796+sankalp04@users.noreply.github.com>
Co-authored-by: Jonathan Harper <jharper+moar@unity3d.com>
Co-authored-by: Ruo-Ping (Rachel) Dong <dongruoping@gmail.com>
Co-authored-by: Nancy Iskander <n2iskand@uwaterloo.ca>
Co-authored-by: Nancy Iskander <nancyiskanderonline@gmail.com>
Co-authored-by: Ruo-Ping Dong <ruoping.dong@unity3d.com>
Co-authored-by: Andrew Cohen <andrew.cohen@unity3d.com>
* test initalize steps to 100
* use mean of first trajectory to initialize the normalizer
* remove blank line
* update changelog
* cleaned up initialization of variance/mean
* large normalization obs unit test
* add --upgrade to pip to get newer downloader (#4338)
* Fix format of the changelog for validation. (#4340)
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
Co-authored-by: Chris Goy <christopherg@unity3d.com>
* Update versions for release 4
* Link validation file should ignore itself
* Remove 'unreleased' section from changelog
* Change to 0.18.0 for python versions
* also update extensions package version
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Introduced the Constant Parameter Sampler that will be useful later as samplers and floats can be used interchangeably
* Refactored the settings.py to refect the new format of the config.yaml
* First working version
* Added the unit tests
* Update to Upgrade for Updates
* fixing the tests
* Upgraded the config files
* Fixes
* Additional error catching
* addressing some comments
* Making the code nicer with cattr
* Added and registered an unstructure hook for PrameterRandomization
* Updating C# Walljump
* Adding comments
* Add test for settings export (#4164)
* Add test for settings export
* Update ml-agents/mlagents/trainers/tests/test_settings.py
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
* Including environment parameters for the test for settings export
* First documentation update
* Fixing a link
* Updating changelog and migrating
* adding some more tests for the conversion script
* fixing bugs and using samplers in the walljump curriculum
* Changing the format of the curriculum file as per discussion
* Addressing comments
* Update ml-agents/mlagents/trainers/settings.py
Co-authored-by: Ervin T. <ervin@unity3d.com>
* Update docs/Migrating.md
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* addressing comments
Co-authored-by: Ervin T <ervin@unity3d.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
Ervin T
Chris Goy
Chris Elion
vincentpierre
andrewcoh
Arthur Juliani
brccabral
Ruo-Ping Dong
ykeuter