* added broadcast to the player and heuristic brain.
Allows the python API to record actions taken along with the states and rewards
* removed the broadcast checkbox
Added a Handshake method for the communicator
The academy will try to handshake regardless of the brains present
Player and Heuristic brains will send their information through the communicator but will not receive commands
* bug fix : The environment only requests actions from external brains when unique
* added warning in case no brins are set to external
* fix on the instanciation of coreBrains,
fix on the conversion of actions to arrays in the BrainInfo received from step
* default discrete action is now 0
bug fix for discrete broadcast action (the action size should be one in Agents.cs)
modified Tennis so that the default action is no action
modified the TemplateDecsion.cs to ensure non null values are sent from Decide() and MakeMemory()
* minor fixes
* need to convert the s...
* More efficiently allocate memory when sending states
* Code clean-up
* Additional changes
* More GC reduction
* Remove state list initialization from example environments
* Use built-in json tool to serialize state message
* Remove commented code
* Use more efficient CompareTag
* Comments before code
* Use type inference where appropriate
Greatly simplified GridWorld code. It now also only uses a visual observation rather than state vector in order to demonstrate learning purely from a visual input.
* `learn.py` is now main script for training brains.
* Simultaneous multi-brain training is now possible.
* `ghost-trainer` allows for proper training in adversarial scenarios.
* `imitation-trainer` provides a basic implementation of real-time behavioral cloning.
* All trainer hyperparameters now exist in `.yaml` files.
* `PPO.ipynb` removed.
* LSTM model added.
* More dynamic buffer class to handle greater variety of scenarios.
* Add support for stacking past n states to allow network to learn temporal dependencies.
* Add Banana Collector environment for demonstrating partially observable multi-agent environments.
* Add 3DBall Hard which lacks velocity information in state representation. Used as test for LSTM and state-stacking features.
* Rework Tennis environment to be continuous control and trainable in 100k steps.
Replaced the print statements with logging statements in the exception.py file
Uses the same logger as the environment one
named the logger unityagents
* Add ability to seed learning (numpy, tensorflow, and Unity) with `--seed` flag.
* Add `maxStepReached` flag to Agents and Academy.
* Change way value bootstrapping works in PPO to take advantage of timeouts.
* Default size of GridWorld changed to 5x5 in order to validate bootstrapping changes.
* Implement behavioral cloning for cc/dc, fc/rnn, state/observations.
* Re-organize folder structure in anticipation of unitytrainers as a package.
* Create demo environment BananaImitation to validate behavioral cloning.
* Fixes#336
* Reorganized python tests into separate folder, and make individiual test files for different (sub) modules.
* Add tests for trainer_controller, PPO, and behavioral cloning. More to come soon.
* Minor bug fixes discovered while writing tests.
* Reworked GirdWorld to reset much faster.
* Cleaned ObservationToTex and reworked GetObservationMatrixList to be 3x faster.
* On Demand Decision : Use RequestDecision and RequestAction
* New Agent Inspector : Use it to set On Demand Decision
* New BrainParameters interface
* LSTM memory size is now set in python
* New C# API
* Semantic Changes
* Replaced RunMDP
* New Bouncer Environment to test On Demand Dscision
* [Previous Text Actions] Renamed previous_action to previous_vector_action
added previous_text_action to the BrainInfo
* [Semantics] Carried the modifications to the semantics of previous_vector_action to the trainers
* [containers] Enables container support for scenes that use visual observations
* [Initial Commit] Works only with simple balance ball
* [Optimiztion] Store the academy in the brainBatcher as a temporary measure
* [Modifications] Made it work from the editor as a prototype
* [Made socket communicator and reimplmented all functionalities]
* [Forgotten file] removed .meta file
* [Forgot the meta file]
* [Metafile] deleted metafile
* [Comments] Removed dead code
* [Comments] Added some descriptions
* [Bug Fix] Multi brain scenario
* [improved AgentInfo converter]
* [Optimization] Remove VectorObs since StackedVectorObs is present in the AgentInfo protobuf object
* [Timeout] Implemented a timeout for the rpc communicator in Unity
* [Libraries] Added the C# Protobuf and Grpc libraries
* [Requirements] Added protobuf 3.5.2 to the requirements
* [Code Formating] Removed dead code and split some lines
...
* [Initial Commit]
Modified the model.py file and the ppo/trainer.py file to use masked actions
* Preliminary modifications to the python side of the code to enable action masking
* Preliminary modifications to the C# side of the code to enable action masking
* Preliminary modifications to the communication side of the code to enable action masking
* Implemented action masking for BC
Note : The actions of the teacher are not masked
* More error messages for the action masking
* fix pytests
* Added Documentation
* Address comment
* Addressed Comments on docs
* Addressed second comment on docs
* Addressed comments for the python side of the code
* Created the action masker and associated unit tests
* Addressed comments on the C# side
* Addressed the comment regarding action_masking_name
* Addressed the comments
* Initial Commit
Ported most functionalities, still need to :
- Documentation
- Add Comments
- Custom drawer for BrainParameters
- Fix the UnitTests
- Review Functionalities
* Added Custom Drawer for the Brain Parameters
* Improvements to the HubDrawer
* Modified the Brain Editors
* Minor bug fixes and UI changes
* Modified the Help Boxes of the Drawers
* Modified Brain class, renamed Initialize and made DecideAction virtual
* Fix the UnityTests
* Simpler Brain creation menu
* Renamed Internal Brain to Learning Brain
* modified the parameters to remove reference to External or Internal in the Protobuf objects
* Updated the protobuf generated files
* Fix the Pytests
* Removed the graph scope from the Learning Brain
* cleaner logic than try catch
* Removed the isExternal field of the brain and put the isTraining logic into LearningBrain and Training Hub
* Modified how the Brain finds the A...
* Check that worker port is available in RpcCommunicator
Previously the RpcCommunicator did not check the port or create the
RPC server until `initialize()` was called. Since "initialize"
requires the environment to be available, this means we might create
a new environment which connects to an existing RPC server running
in another process. This causes both training runs to fail.
As a remedy to this issue, this commit moves the server creation into
the RpcCommunicator constructor and adds an explicit socket binding
check to the requested port.
* Fixes suggested by Codacy
* Update rpc_communicator.py
* Addressing feedback: formatting & consistency
We check for the single brain case in UnityEnvironment by checking
for applicable non-dict types in the step arguments. However for ints
and floats we just use `np.int_` and `np.float_` for the check, which
are the defaults for your system.
This means if you are using an application (like baselines in #1448)
which uses the wrong int/float size an error will be thrown. This
change explicitly allows both 32 and 64-bit numbers.
* Ticked API :
- Ticked API for pypi for mlagents
- Ticked API for pypi for unity-gym
- Ticked Communication number for API
- Ticked Model Loader number for API
* Ticked the API for the pytest
Removing this function breaks some tests, and the only way around
this at this time is a bigger refactor or hacky fixes to tests.
For now, I'd suggest we just revert this small part of a change
and keep a refactor in mind for the future.
This commit adds support for running Unity environments in parallel.
An abstract base class was created for UnityEnvironment which a new
SubprocessUnityEnvironment inherits from.
SubprocessUnityEnvironment communicates through a pipe in order to
send commands which will be run in parallel to its workers.
A few significant changes needed to be made as a side-effect:
* UnityEnvironments are created via a factory method (a closure)
rather than being directly created by the main process.
* In mlagents-learn "worker-id" has been replaced by "base-port"
and "num-envs", and worker_ids are automatically assigned across runs.
* BrainInfo objects now convert all fields to numpy arrays or lists to
avoid serialization issues.
- Ticked API for pypi for mlagents
- Ticked API for pypi for mlagents_envs
- Ticked Communication number for API
- Ticked API for unity-gym
* Ticked the API for the pytest
SubprocessUnityEnvironment sends an environment factory function to
each worker which it can use to create a UnityEnvironment to interact
with. We use Python's standard multiprocessing library, which pickles
all data sent to the subprocess. The built-in pickle library doesn't
pickle function objects on Windows machines (tested with Python 3.6 on
Windows 10 Pro).
This PR adds cloudpickle as a dependency in order to serialize the
environment factory. Other implementations of subprocess environments
do the same:
https://github.com/openai/baselines/blob/master/baselines/common/vec_env/subproc_vec_env.py
On Windows the interrupt for subprocesses works in a different
way from OSX/Linux. The result is that child subprocesses and
their pipes may close while the parent process is still running
during a keyboard (ctrl+C) interrupt.
To handle this, this change adds handling for EOFError and
BrokenPipeError exceptions when interacting with subprocess
environments. Additional management is also added to be sure
when using parallel runs using the "num-runs" option that
the threads for each run are joined and KeyboardInterrupts are
handled.
These changes made the "_win_handler" we used to specially
manage interrupts on Windows unnecessary, so they have been
removed.
A change was made to the way the "train_mode" flag was used by
environments when SubprocessUnityEnvironment was added which was
intended to be part of a separate change set. This broke the CLI
'--slow' flag. This change undoes those changes, so that the slow
/ fast simulation option works correctly.
As a minor additional change, the remaining tests from top level
'tests' folders have been moved into the new test folders.
When using parallel SubprocessUnityEnvironment instances along
with Academy Done(), a new step might be taken when reset should
have been called because some environments may have been done while
others were not (making "global done" less useful).
This change manages the reset on `global_done` at the level of the
environment worker, and removes the global reset from
TrainerController.
* WIP precommit on top level
* update CI
* circleci fixes
* intentionally fail black
* use --show-diff-on-failure in CI
* fix command order
* rebreak a file
* apply black
* WIP enable mypy
* run mypy on each package
* fix trainer_metrics mypy errors
* more mypy errors
* more mypy
* Fix some partially typed functions
* types for take_action_outputs
* fix formatting
* cleanup
* generate stubs for proto objects
* fix ml-agents-env mypy errors
* disallow-incomplete-defs for gym-unity
* Add CI notes to CONTRIBUTING.md
Previously in v0.8 we added parallel environments via the
SubprocessUnityEnvironment, which exposed the same abstraction as
UnityEnvironment while actually wrapping many parallel environments
via subprocesses.
Wrapping many environments with the same interface as a single
environment had some downsides, however:
* Ordering needed to be preserved for agents across different envs,
complicating the SubprocessEnvironment logic
* Asynchronous environments with steps taken out of sync with the
trainer aren't viable with the Environment abstraction
This PR introduces a new EnvManager abstraction which exposes a
reduced subset of the UnityEnvironment abstraction and a
SubprocessEnvManager implementation which replaces the
SubprocessUnityEnvironment.
* Timer proof-of-concept
* micro optimizations
* add some timers
* cleanup, add asserts
* Cleanup (no start/end methods) and handle exceptions
* unit test and decorator
* move output code, add a decorator
* cleanup
* module docstring
* actually write the timings when done with training
* use __qualname__ instead
* add a few more timers
* fix mock import
* fix unit test
* don't need fwd reference
* cleanup root
* always write timers, add comments
* undo accidental change
SubprocessEnvManager takes steps synchronously to reproduce old
behavior, meaning all parallel environments will need to wait for
the slowest environment to take a step. If some steps take much
longer than others, this can lead to a substantial overall slowdown
in practice. We've seen extreme cases where we see almost a 2x
speedup from using asynchronous stepping, with no downside for our
faster environments. (Bouncer 16% improvement, Walker 14% improvement
in tests).
This PR changes the SubprocessEnvManager to use async stepping.
This means on the "step" call the environment manager will enqueue
step requests to workers, and then only wait until at least one
step has been completed before returning.
* Timer proof-of-concept
* micro optimizations
* add some timers
* cleanup, add asserts
* Cleanup (no start/end methods) and handle exceptions
* unit test and decorator
* move output code, add a decorator
* cleanup
* module docstring
* actually write the timings when done with training
* use __qualname__ instead
* add a few more timers
* fix mock import
* fix unit test
* get timers from worker process (WIP)
* clean up timer merging
* typo
* WIP
* cleanup merging code
* bad merge
* undo accidental change
* remove reset command
* fix style
* fix unit tests
* fix unit tests (they got overwrote in merge)
* get timer root though a function
* timer around communicate
* Add Sampler and SamplerManager
* Enable resampling of reset parameters during training
* Documentation for Sampler and example YAML configuration file
This fixes an issue where stopping the game when training in the Editor won't end training, due to the new asynchronous SubprocessEnvManager changes. Another minor change was made to move the `env_manager.close()` in TrainerController to the end of `start_learning` so that we are more likely to save the model if something goes wrong during the environment shutdown (this occurs sometimes on Windows machines).
- Fix issue with BC Trainer `increment_steps`.
- Fix issue with Demonstration Recorder and visual observations (memory leak fix was deleting vis obs too early).
- Make Samplers sample from the same random seed every time, so generalization runs are repeatable.
- Fix crash when using GAIL, Curiosity, and visual observations together.
* Initial Commit
* Remove the Academy Done flag from the protobuf definitions
* remove global_done in the environment
* Removed irrelevant unitTests
* Remove the max_step from the Academy inspector
* Removed global_done from the python scripts
* Modified and removed some tests
* This actually does not break either curriculum nor generalization training
* Replace global_done with reserved.
Addressing Chris Elion's comment regarding the deprecation of the global_done field. We will use a reserved field to make sure the global done does not get replaced in the future causing errors.
* Removed unused fake brain
* Tested that the first call to step was the same as a reset call
* black formating
* Added documentation changes
* Editing the migrating doc
* Addressing comments on the Migrating doc
* Addressing comments :
- Removing dead code
- Resolving forgotten merged conflicts
- Editing documentations...
We have been ignoring unused imports and star imports via flake8. These are
both bad practice and grow over time without automated checking. This
commit attempts to fix all existing import errors and add back the corresponding
flake8 checks.
* Feature Deprecation : Online Behavioral Cloning
In this PR :
- Delete the online_bc_trainer
- Delete the tests for online bc
- delete the configuration file for online bc training
* Deleting the BCTeacherHelper.cs Script
TODO :
- Remove usages in the scene
- Documentation Edits
*DO NOT MERGE*
* IMPORTANT : REMOVED ALL IL SCENES
- Removed all the IL scenes from the Examples folder
* Removed all mentions of online BC training in the Documentation
* Made a note in the Migrating.md doc about the removal of the Online BC feature.
* Modified the Academy UI to remove the control checkbox and replaced it with a train in the editor checkbox
* Removed the Broadcast functionality from the non-Learning brains
* Bug fix
* Note that the scenes are broken since the BroadcastHub has changed
* Modified the LL-API for Python to remove the broadcasting functiuonality.
* All unit tests are running
* Modifie...
* Feature Deprecation : Online Behavioral Cloning
In this PR :
- Delete the online_bc_trainer
- Delete the tests for online bc
- delete the configuration file for online bc training
* Deleting the BCTeacherHelper.cs Script
TODO :
- Remove usages in the scene
- Documentation Edits
*DO NOT MERGE*
* IMPORTANT : REMOVED ALL IL SCENES
- Removed all the IL scenes from the Examples folder
* Removed all mentions of online BC training in the Documentation
* Made a note in the Migrating.md doc about the removal of the Online BC feature.
* Modified the Academy UI to remove the control checkbox and replaced it with a train in the editor checkbox
* Removed the Broadcast functionality from the non-Learning brains
* Bug fix
* Note that the scenes are broken since the BroadcastHub has changed
* Modified the LL-API for Python to remove the broadcasting functiuonality.
* All unit tests are running
* Modified the scen...
* ISensor and SensorBase
* camera and rendertex first pass
* use isensors for visual obs
* Update gridworld with CameraSensors
* compressed obs for reals
* Remove AgentInfo.visualObservations
* better separation of train and inference sensor calls
* compressed obs proto - need CI to generate code
* int32
* get proto name right
* run protoc locally for new fiels
* apply generated proto patch (pyi files were weird)
* don't repeat bytes
* hook up compressedobs
* dont send BrainParameters until there's an AgentInfo
* python BrainParameters now needs an AgentInfo to create
* remove last (I hope) dependency on camerares
* remove CameraResolutions and AgentInfo.visual_observations
* update mypy-protobuf version
* cleanup todos
* python cleanup
* more unit test fixes
* more unit test fix
* camera sensors for VisualFood collector, record demo
* SensorCompon...
* Initial commit removing memories from C# and deprecating memory fields in proto
* initial changes to Python
* Adding functionalities
* Fixes
* adding the memories to the dictionary
* Fixing bugs
* tweeks
* Resolving bugs
* Recreating the proto
* Addressing comments
* Passing by reference does not work. Do not merge
* Fixing huge bug in Inference
* Applying patches
* fixing tests
* Addressing comments
* Renaming variable to reflect type
* test
When we initially connect to the environment using RPCCommunicator,
the connection is polled so we don't hang forever on `.recv()` when
the environment wasn't launched or failed. However we don't currently
have any similar check for the exchanges mid-training-run.
This change applies the same timeout from initialization to each exchange,
and extends the default `timeout_wait` to 60 seconds to generally improve
the chances we won't have a mismatch between environment launch time and
the trainer timeout.
Tested on: single-env and multi-env cases. Killed 1 environment process
manually and saw that the model was saved appropriately and all processes
closed.
* Update package and communicator versions to 0.11
* Remove pip cache fallback for CircleCI
This change removes the caching fallback in the case where dependencies
change, since it can cause CI failures when we have incompatible
dependencies in the cache.
* Limit Tensorflow version for tests to <2.0
* Use stable bokken image. (#2815)
* build fixes for 2018+ (#2808)
* rename CompressionType enum
* fix standalone build test for 2018+
* Add more editor versions for testing. (#2809)
* class variable for API verison, fix env tests (#2817)
* fixed area prefab
agents were pointing to the wrong laser gameObject.
* 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
* allow --version argument in mlagents-learn
* Develop version print add strings (#2945)
* add __version__ to libs
* more version info
* use actual version
* [WIP] Side Channel initial layout
* Working prototype for raw bytes
* fixing format mistake
* Added some errors and some unit tests in C#
* Added the side channel for the Engine Configuration. (#2958)
* Added the side channel for the Engine Configuration.
Note that this change does not require modifying a lot of files :
- Adding a sender in Python
- Adding a receiver in C#
- subscribe the receiver to the communicator (here is a one liner in the Academy)
- Add the side channel to the Python UnityEnvironment (not represented here)
Adding the side channel to the environment would look like such :
```python
from mlagents.envs.environment import UnityEnvironment
from mlagents.envs.side_channel.raw_bytes_channel import RawBytesChannel
from mlagents.envs.side_channel.engine_configuration_channel import EngineConfigurationChannel
channel0 = RawBytesChannel()
channel1 = EngineConfigurationChannel()
env = UnityEnvironme...
* [WIP] Side Channel initial layout
* Working prototype for raw bytes
* fixing format mistake
* Added some errors and some unit tests in C#
* Added the side channel for the Engine Configuration. (#2958)
* Added the side channel for the Engine Configuration.
Note that this change does not require modifying a lot of files :
- Adding a sender in Python
- Adding a receiver in C#
- subscribe the receiver to the communicator (here is a one liner in the Academy)
- Add the side channel to the Python UnityEnvironment (not represented here)
Adding the side channel to the environment would look like such :
```python
from mlagents.envs.environment import UnityEnvironment
from mlagents.envs.side_channel.raw_bytes_channel import RawBytesChannel
from mlagents.envs.side_channel.engine_configuration_channel import EngineConfigurationChannel
channel0 = RawBytesChannel()
channel1 = EngineConfigurationChanne...
* initial commit for LL-API
* fixing ml-agents-envs tests
* Implementing action masks
* training is fixed for 3DBall
* Tests all fixed, gym is broken and missing documentation changes
* adding case where no vector obs
* Fixed Gym
* fixing tests of float64
* fixing float64
* reverting some of brain.py
* removing old proto apis
* comment type fixes
* added properties to AgentGroupSpec and edited the notebooks.
* clearing the notebook outputs
* Update gym-unity/gym_unity/tests/test_gym.py
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* Update gym-unity/gym_unity/tests/test_gym.py
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* Update ml-agents-envs/mlagents/envs/base_env.py
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* Update ml-agents-envs/mlagents/envs/base_env.py
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* addressing first comments
* NaN checks for r...
* pass shape to WriteAdapter
* handle floats on python side
* cleanup
* whitespace
* rename GetFloatObservationShape, support uncompressed in RenderTexture sensor
* numpy float32
* remove unused using
* Float sensor and unit test
* replace asserts with exceptions, docstrings
* Make ChannelId a property and renamed ReservedChannelId
* Changes on the Python side for consistency
* Modified the tutorial appropriately
* fixing bugs
* Update ml-agents-envs/mlagents_envs/environment.py
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* Update com.unity.ml-agents/Runtime/Grpc/RpcCommunicator.cs
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* Addressing comments
* Update docs/Python-API.md
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* Added a Utils class on the side channel (#3447)
- No change in user facing API
- Simplifies the code in the side channel implementations as it makes it easier to check if a side channel id is within ranges
- No changes to tests
- No changes to Documentation
* Simplifying
* Fixing a bug
* Replace the int ChannelId with a GUID/UUID ChannelId (#3454)
* renaming channel_type to channel_id
* Making the constant GUID const...
* Bumping versions on master
* Bumping package version
* Made the package version 0.15.0-preview
* Reverting the API version that was bumped by mistake
* [bug-fix] Increase height of wall in CrawlerStatic (#3650)
* [bug-fix] Improve performance for PPO with continuous actions (#3662)
* Corrected a typo in a name of a function (#3670)
OnEpsiodeBegin was corrected to OnEpisodeBegin in Migrating.md document
* Add Academy.AutomaticSteppingEnabled to migration (#3666)
* Fix editor port in Dockerfile (#3674)
* Hotfix memory leak on Python (#3664)
* Hotfix memory leak on Python
* Fixing
* Fixing a bug in the heuristic policy. A decision should not be requested when the agent is done
* [bug-fix] Make Python able to deal with 0-step episodes (#3671)
* adding some comments
Co-authored-by: Ervin T <ervin@unity3d.com>
* Remove vis_encode_type from list of required (#3677)
* Update changelog (#3678)
* Shorten timeout duration for environment close (#3679)
The timeout duration for closing an environment was set to the
same duration as the timeout when waiting ...
The timeout duration for closing an environment was set to the
same duration as the timeout when waiting for a response from the
still-running environment. This led to long waits for the error
response when communication version wasn't matching.
This change forces a timeout duration of 0 when handling errors.
The "docker target" feature and associated command-line flag
--docker-target-name were created for use with the now-deprecated
Docker setup. This feature redirects the paths used by learn.py
for the environment and config files to be based from a directory
other than the current working directory. Additionally it wrapped
the environment execution with xvfb-run.
This commit removes the "docker target" feature because:
* Renaming the paths doesn't fix any problem. Absolute paths can
already be passed for configs and environment executables.
* Use of xserver, Xvfb, or xvfb-run are independent of mlagents-learn
and can be used outside of the mlagents-learn call. Further, xvfb-run
is not the only solution for software rendering.
* [skip ci] WIP : Modify the base_env.py file
* [skip ci] typo
* [skip ci] renamed some methods
* [skip ci] Incorporated changes from our meeting
* [skip ci] everything is broken
* [skip ci] everything is broken
* [skip ci] formatting
* Fixing the gym tests
* Fixing bug, C# has an error that needs fixing
* Fixing the test
* relaxing the threshold of 0.99 to 0.9
* fixing the C# side
* formating
* Fixed the llapi integratio test
* [Increasing steps for testing]
* Fixing the python tests
* Need __contains__ after all
* changing the max_steps in the tests
* addressing comments
* Making env_manager logic clearer as proposed in the comments
* Remove duplicated logic and added back in episode length (#3728)
* removing mentions of multi-agent in gym and changed the docstring in base_env.py
* Edited the Documentation for the changes to the LLAPI (#3733)
* Edite...
* [API] Make the DecisionRequester public and add a delegate to its API to allow users to customize it's behavior.
- Rename Academy.AgentSetStatus to Academy.AgentPreStep and make it public.
- Fix Unity library cache issues for backwards compatibility tests.
- Collect standalone build and logs to artifacts for standalone build jobs.
- cat standalone build log if the build fails.
- Default verbose to False for standalone build test.
* disable backward compatibility test, bump communication version.
* still run training tests on latest.
* fix yml parse error.
* [communication] Use semantic versioning to test communication compatibility between C# and Python.
- Add tests for the change.
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Make EnvironmentParameters a first-class citizen in the API
Missing: Python conterparts and testing.
* Minor comment fix to Engine Parameters
* A second minor fix.
* Make EngineConfigChannel Internal and add a singleton/sealed accessor
* Make StatsSideChannel Internal and add a singleton/sealed accessor
* Changes to SideChannelUtils
- Disallow two sidechannels of the same type to be added
- Remove GetSideChannels that return a list as that is now unnecessary
- Make most methods except (register/unregister) internal to limit users impacting the “system-level” side channels
- Add an improved comment to SideChannel.cs
* Added Dispose methods to system-level sidechannel wrappers
- Specifically to StatsRecorder, EnvironmentParameters and EngineParameters.
- Updated Academy.Dispose to take advantage of these.
- Updated Editor tests to cover all three “system-level” side channels.
Kudos to Unit Tests (TestAcade...
* write release_tag too
* fix leading empty line
* update circle jobs and release tag logic
* set default to empty string
* set release tag, add sanity check
* Removed the default for width and height of the executable training. This is to help relove #3835 since setting the screen resolution on Linux 2019.3 can cause issues.
* Editing the changelog
* Making fields in EngineConfig optional
* [bug-fix] Fix issue with initialize not resetting step count (#3962)
* Develop better error message for #3953 (#3963)
* Making the error for wrong number of agents raise consistently
* Better error message for inputs of wrong dimensions
* Fix#3932, stop the editor from going into a loop when a prefab is selected. (#3949)
* Minor doc updates to release
* add unit tests and fix exceptions (#3930)
Co-authored-by: Ervin T <ervin@unity3d.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
Co-authored-by: Chris Goy <christopherg@unity3d.com>
* Fix typo
* Made a side channel utils to reduce the complexity of UnityEnvironment
* Added a get_side_channel_dict utils method
* Better executable launcher (unarguably)
* Fixing the broken test
* Addressing comments
* [skip ci] Update ml-agents-envs/mlagents_envs/side_channel/side_channel_manager.py
Co-authored-by: Jonathan Harper <jharper+moar@unity3d.com>
* No catch all
Co-authored-by: Jonathan Harper <jharper+moar@unity3d.com>
* Replaced get_behavior_names and get_behavior_spec with behavior_specs property
* Fixing the test
* [ci]
* addressing some comments
* use typing.Mapping (#3948)
* Update ml-agents-envs/mlagents_envs/base_env.py
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Adding the documentation
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Making some things private in UnityEnvironment
* Readding the default ports as public
* removing _SCALAR_ACTION_TYPES and _SINGLE_BRAIN_ACTION_TYPES
* Removing unused method
* [WIP] Unity Environment Registry
[JIRA ticket](https://jira.unity3d.com/browse/MLA-997)
[Design Document](https://docs.google.com/document/d/1bFQ3_oXsA80FMou8kwqYxC53kqG5L3i0mbTQUH4shY4/edit#)
In This PR : Prototype of the Unity Environment Registry
Uploaded the 3DBall and Basic Environments for mac only
How to use on Python :
```python
from mlagents_envs.registry import UnityEnvRegistry
registry = UnityEnvRegistry()
print(registry["3DBall"].description)
env = registry["3DBall"].make()
env.reset()
for i in range(10):
print(i)
env.step()
env.close()
```
* Other approach:
- UnityEnvRegistry is no longer static and needs to be instantiated
- Providing a default_registry that will contains our environments
- Added a functionality to register RemoteRegistryEntry with a yaml file
* Some extra verification of the url : The binary will have a hash of the url in its name to make sure the right environ...
* Added a random action creator on the BehaviorSpecs
* Bumping numpy version
* Bumping numpy version
* Not using np.random.Generator as it seems to still be under developement
Updates to CameraSensor / CameraSensorComponent:
* new settings object to set up layer masks, depth, etc
* support for arbitrary # channels returned by the sensor
* channels include depth, layer mask, RGB, or grayscale
Updates to VisualFoodCollector:
* food doesn't roll (for now), simplifies learning without stacking
* added layers
Updates to mlagents_envs:
* decode multiple pngs packed into a single observation
* 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...
* 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>
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>
* Add hybrid action capability flag (#4576)
* Change BrainParametersProto to support ActionSpec (#4579)
* Assign new BrainParametersProto fields based on capabilities (#4581)
* ActionBuffer with hybrid actions for RemotePolicy (#4592)
* Barracuda inference for hybrid actions (#4611)
* Refactor BarracudaModel loader checks (#4629)
* Export separate nodes for continuous/discrete actions (#4655)
* Separate continuous/discrete actions in AgentActionProto (#4698)
* Force different nodes for new and deprecated action output (#4705)
* remove group id
* very rough sketch for TeamManager interface
* add team manager id to proto
* team manager for hallway
* add manager to hallway
* send and process team manager id
* remove print
* small cleanup
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
- 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.
* Make buffer type-agnostic
* Edit types of Apped method
* Change comment
* Collaborative walljump
* Make collab env harder
* Add group ID
* Add collab obs to trajectory
* Fix bug; add critic_obs to buffer
* Set group ids for some envs
* Pretty broken
* Less broken PPO
* Update SAC, fix PPO batching
* Fix SAC interrupted condition and typing
* Fix SAC interrupted again
* Remove erroneous file
* Fix multiple obs
* Update curiosity reward provider
* Update GAIL and BC
* Multi-input network
* Some minor tweaks but still broken
* Get next critic observations into value estimate
* Temporarily disable exporting
* Use Vince's ONNX export code
* Cleanup
* Add walljump collab YAML
* Lower max height
* Update prefab
* Update prefab
* Collaborative Hallway
* Set num teammates to 2
* Add config and group ids to HallwayCollab
* Fix bug with hallway collab
* E...
* [Bug Fix] set_action_for_agent expects a ActionTuple with batch size 1.
* moving a line around
(cherry picked from commit aac2ee6cb650e6969a6d8b9f7c966f69b9e2df04)
* Fixing networks.py for the merge
* fix compile error
* Adding the goal conditioning sensors with the new observation specs
* addressing feedback
* I forgot to change the m_observationType
* Renaming Goal to GoalSignal (#5190)
* Renaming GOAL to GOAL_SIGNAL
* VectorSensorComponent to use new API
* Adding docstrings
* verbose pytest on github action
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
* Python Low Level API Documentation
Added Python Low Level API Documentation in addition to How to Use document. Added link to API documentation in How to Use document.
* Fixed pre-commit issues with docstrings in mlagents-env base_env
* Added local precommit hook to autogenerate markdown documentation using pydoc-markdown
* Updated github precommit workflow to install pydoc-markdown
* Updated github precommit workflow to fix pydoc-markdown install order.
* Some refactoring and docstring updates.
* Removed modules from doc generation as per https://github.com/Unity-Technologies/ml-agents/pull/5325#discussion_r632838268
* Some edits to the documentation (#5369)
* Some edits to the documentation
* fix precommit
* Update ml-agents-envs/mlagents_envs/base_env.py
* regenerating markdown
* Added fixed version to pydoc-markdown precommit install.
* Updated docs readme to add link to new Python API document...
Arthur Juliani
vincentpierre
GitHub
eshvk
Vincent Gao
Marwan Mattar
Joe Ward
Deric Pang
Jonathan Harper
Vincent-Pierre BERGES
Ervin T
Chris Elion
sankalp04
Ervin Teng
Andrew Cohen
Anupam Bhatnagar
Alphonso Crawford
Christopher Goy
HH
Ruo-Ping Dong
Scott Jordan
brccabral
Miguel Alonso Jr