Release 0.10.0 #2648
Merged
Release 0.10.0 #2648
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 0.9.2 to develop
Fixed small typo in documentation.
* specify dirs, exclude test files * update comments * html coverage in CI artifacts * add destination * ignore coverage files * check gym-unity too
- Reduces memory usage of buffer.
* Fix bug with construct_curr_info * Add more tests
* initialize trainer step count * remove step init from RLTrainer
* Add Soft Actor-Critic model, trainer, and policy and sac_trainer_config.yaml * Add documentation for SAC and tweak PPO documentation to reference the new pages. * Add tests for SAC, change simple_rl test to run both PPO and SAC.
) * This addresses #1835. Baselines expects single environments used with their ppo2 algorithm to be wrapped in a DummyVecEnv. The old readme did not instruct the reader to do so and the code failed to run with the latest version of baselines. This imports the correct function from baselines and fixes the make_unity_env function described in the readme. * added line to gym-unity/README.md to note the version of baselines the examples were tested with
This change was requested for clarity during the async EnvManager PR. It's a simple rename of the StepInfo class.
Merege 0.9.3 changes to develop
* unit test - don't use global random generator * Update test_simple_rl.py
Clean up SAC config
…ne-bc Update the offline_bc_config path
… the test will not randomly fail (#2520)
* initialize random instance correctly * restore threshold (I hope)
Only cosmetic and readability improvements. No functional changes were intended. Utilities.cs - Fixed comments across file - Made class static - Removed unnecessary imports - Removed unused method arguments - Renamed variables as appropriate to make usage clearer - In AddRangeNoAlloc, disabled (by comment) Rider’s suggestion to revert to use of built-in Range field (Fixed) - In TextureToTensorProxy, swapped order of first two arguments to be more in-line with convention of input, output UtilitiesTests.cs - Removed unnecessary imports - Simplified array creation commands GeneratorImp.cs - Rider automatically deleted spaces on empty lines - Changed call to TextureToTensorProxy to mirror new argument ordering * Clean-up to UnityAgentsException.cs - Removed unnecessary imports - Fixed comment warning - Fixed method header * Improvements to Startup.cs - Created const for SCENE_NAME field - Fixed string formatting for exception message - Added new line at EOF * Adding team-wide settings file * Clean up to RandomNormal - Removed FillTensor from RandomNormal and moved to TensorUtils - Removed the tests in RandomNormalTest that are for FillTensor to TensorUtilsTest - Fixed GeneratorImpl to use to TensorUtils.FillTensor method * Decouples DiscreteActionOutputApplier from Multinomial - Add use of var where appropriate - Makes variables readonly where appropriate - Makes private variables start with “_” - Removes DiscreteActionOutputApplier context from Multinomial - class is much simpler now - Moves most of the tests in MultinomialTest to a new DiscreteActionOutputApplierTest class - Adds a basic Multinomial test to MultinomialTest * Minor formatting to TensorProxy - Limiting code to 100 characters - renaming private vars to start with “_” - fixing indentation in file Couple of other minor fixes to TensorUtilsTest and Discrete…Test.cs * Adding new line to EOF for TensorProxy * Adding missing meta files. * Removing three unused methods from TensorProxy * (Big) Rename of TensorProxy fields Changed Name —> name; ValueType —> valueType; Shape —> shape; Data —> data * Additional cosmetic changes to a number of files previously modified - Limit to 100 chars per line - Appropriate formatting - Removed Rider warnings * Improvements to Multinomial(Test).cs Fixed the tests for Multinomial as they didn’t include cumulative mass functions. Also, improved the documentation.
* Add a note on Custom messages about needing trainer changes * move to top (aside doesn't render as expected) * Don't blockquote * Update wording
* [memory] Fix for tensors not being disposed of. * Fix member name.
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.
This wasn't working before because of several remaining partially defined function definitions.
…DKlog Remove UnitySDK.log file
* encapsulate commandline args * fix tests * add tests on cmdline parsing * cleanup * remove docopt * simplify --slow
* TensorFlowSharp is no more * Removed old documents
* Added option to use environment arguments in learn * hook into argparse * add example to readme
Our multi-GPU training had a regression such that freezing the graph was broken. This change fixes that issue by making a few changes: * Removes the top level "tower" variable scope added by multi-GPU so that the output nodes have correct names * Removes the use of "freeze_graph" and replaces it with our own similar functionality. * Adds the "auto reuse" to network layers which require them
* image decompress timer * dont lazy load the image
…cy brain, we will remove the action descriptions from the dictionary of things we need to compare. This is to prevent the case where a user has different descriptions for his actions but still wants to train a brain using expert demonstrations. (#2517)
* WIP cleanup loading * better exceptions for parser errors - refer to online lint tools * feedback - rename variable
* new env styles rebased on develop * added new trained models * renamed food collector platforms * reduce training timescale on WallJump from 100 to 10 * uncheck academy control on walljump * new banner image * rename banner file * new example env images * add foodCollector image * change Banana to FoodCollector and update image * change bouncer description to include green cube * update image * update gridworld image * cleanup prefab names and tags * updated soccer env to reference purple agent instead of red * remove unused mats * rename files * remove more unused tags * update image * change platform to agent cube * update text. change platform to agents head * cleanup * cleaned up weird unused meta files * add new wall jump nn files and rename a prefab * walker change stacked states from 5 to 1 walker collects physics observations so stacked states are not needed * fixed reacher platform and crawlerstatic scene * add more space between agents * adjust x pos of camera based on new agent spacing * adjust colliders & testing new nn models * change speed on hallway agent and make rb continousDynamic also update goal collider size in pushblock * pushblock add new model, crawler decrease spawn radius * reset cube pos each agent reset * added new hallway nn model, fixed goal gameobjects * add new files for 3dball * added new models * fixed crawlerStatic target spawn * Increase bouncer steps * [format] Format code to be complaint with Unity coding conventions. (#2608) * Revert Batcher changes
* Add note about using GPU inference for ResNet
* Tick versions for pip packages * Tick API version to 10
* Re-record demos for new envs * Add better Hallway brain * Remove Banana
* Tweak SAC hyperparams * Make network bigger * Properly report entropy * Revert "Properly report entropy" This reverts commit 383a8d8.
harperj
approved these changes
Sep 30, 2019
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.
Merge Release 0.10.0 into Master. Release notes: https://github.com/Unity-Technologies/ml-agents/releases/tag/untagged-11e16747f20c203bae73