Release v0.7 into master #1764
Merged
Release v0.7 into master #1764
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
release-v0.6 --> develop
Release v0.6 into develop
* Add blurb about using the --load flag in the intro guide, and typo fix. * Add section in tutorial to create multiple area learning environment. * Add mention of Done() method in agent design
* Add option to set gym visual observation to uint8 * Add option to flatten branched discrete actions * Add game_over variable to gym wrapper * Add guide on how to use Dopamine with the gym wrapper and comparisons with Baselines and PPO
…re generic AddVectorObs(IEnumerable<float>) (#1540)
Hotfix 0.6.0a to develop
* Remove env creation logic from TrainerController Currently TrainerController includes logic related to creating the UnityEnvironment, which causes poor separation of concerns between the learn.py application script, TrainerController and UnityEnvironment: * TrainerController must know about the proper way to instantiate the UnityEnvironment, which may differ from application to application. This also makes mocking or subclassing UnityEnvironment more difficult. * Many arguments are passed by learn.py to TrainerController and passed along to UnityEnvironment. This change moves environment construction logic into learn.py, as part of the greater refactor to separate trainer logic from actor / environment.
Add docs for increasing memory limit for Docker for Mac
Minor fix to docs on Docker
* Switched default Mac GFX API to Metal * Added Barracuda pre-0.1.5 * Added basic integration with Barracuda Inference Engine * Use predefined outputs the same way as for TF engine * Fixed discrete action + LSTM support * Switch Unity Mac Editor to Metal GFX API * Fixed null model handling * All examples converted to support Barracuda * Added model conversion from Tensorflow to Barracuda copied the barracuda.py file to ml-agents/mlagents/trainers copied the tensorflow_to_barracuda.py file to ml-agents/mlagents/trainers modified the tensorflow_to_barracuda.py file so it could be called from mlagents modified ml-agents/mlagents/trainers/policy.py to convert the tf models to barracuda compatible .bytes file * Added missing iOS BLAS plugin * Added forgotten prefab changes * Removed GLCore GFX backend for Mac, because it doesn't support Compute shaders * Exposed GPU support for LearningBrain inference * Silenced excessive Barracuda logging. Add scripting define BARRACUDA_VERBOSE to re-enable it. * added model importer for a new NNModel asset * Modified the Python code to export .nn files * renamed all .bytes to .nn * Removed all .tf models * Linked all NNModels to appropriate Brain * Added a TEMPORARY Icon * Update LearningBrain.cs * Removed OpenGL from Player Settings * Added Barracuda model conversion test * Fixed converter test to actually fail when conversion fails * Updated Barracuda to new build * Upgraded to Barracuda v0.1.5. Pre-trained models converted accordingly. * Barracuda : Updating the documentation (#1607) * renamed .bytes to .nn in documentation * Removed references to TensorFlowSharp in docs * Addressed Comments and added a Unity Inference Engine md * deleted dead meta file and added a note on the OpenGLCore Graphics API * Restore global gravity value when Academy gets destroyed * Backup and restore fixedDeltaTime and maximumDeltaTime on Academy init / shutdown * Fixed Barracuda cleanup when brain object gets unloaded * Fixed visual observation order per @vincentpierre request * Improved handling of initial filesystem state * Removed TensorType test to match new PreviousActionInputGenerator logic, which now accepts both integers and floats as Barracuda can't provide tensor type metadata * Cosmetic improvement, #if undefined #endif is not enough to fully comment out compute shader file, #pragma lines still get processed * Fixed Neural Net execution with GPU backend on Samsung Galaxy S8 (global) phones * Temporary disabled Conv2D_L1Cached64_RegisterBlock4x4 as it's causing crash on Galaxy S9 (USA) phones. Looks like a driver bug. * Making the scripting define symbols be either Barracuda or TF# * Barracuda updated to 0.1.6
* added the pypiwin32 package * fixed the break on mac, fixed part of pytest above version 4 * added something to the windows to help unstuck people * resolved the comment
* Update Learning-Environment-Design-Agents.md * Space typo * Word change
* 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
* Added comment on OpenGL 3.0 emulation * Updated line change
* Fix for GRPC, need documentation * Edits * typo * Fixes * Missing typo * Modified the documentation * Updated the documentation
* Change gym-unity tests to use Mock instead of MockCommunicator * move creation of mock objects into helper functions * Fix comment * Fix Codacy errors * Fix ending whitespace * Minor fixes
* Fix typo * Updated some of the scenes
|
🚢 🇮🇹 |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.