Release v0.9.0 #2380
Merged
Release v0.9.0 #2380
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
- Fix slash direction for windows in COMPILER definition - Fix missing COMPILER variables when calling protoc - Fix call to "python" instead of "python3"
- Note to use the windows batch file on windows
- Put rem back in make_fo_win.bat
- Notes for where to enter commands to start with - Select a particular version of grpcio-tools - Note how to get nuget if needed - Directory independent nuget install - Remove instruction to download protoc since it comes with grpc.tools - Add instructions for windows in ##Running and directories for clarification
- Update protobuf folder ignores
- Revert version to what is currently in develop branch to clarify what changed.
- Ignore grpc installation on any platform
- make_for_win_.bat now has the same comment as make.bat - The instructions for editing those files will both use line 7 now.
- Add required version for grpc tools. Newer versions cause UnityToExternalGrpc.cs to fail to compile inside Unity due to a new function in the file
- Include grpc required versions - Clarify which steps are install and which are run every time
- Fix re-install directions to include -e modifer - Move re-install directions from creating-custom... to protobuf readme - Add how to see confirmation that install worked
Markdown for Github shows better with that change
Merge from release 0.8.2 to develop
* 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 * run on whole repo
* 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
…point to clarify is the behaviour of returning a '1' on a **no hit**.
Updated minor typos (sh for console)
Develop rayperception docs
Fix Protobuf Install Instructions
* Create new class (RewardSignal) that represents a reward signal. * Add value heads for each reward signal in the PPO model. * Make summaries agnostic to the type of reward signals, and log weighted rewards per reward signal. * Move extrinsic and curiosity rewards into this new structure. * Allow defining multiple reward signals in YAML file. Add documentation for this new structure.
At each step, an unused `last_reward` variable in the TF graph is updated in our PPO trainer. There are also related unused methods in various places in the codebase. This change removes them.
* fix bug in RandomNormal, add test for distribution * extract epsilon, rename vars
* WIP doesn't crash * return stats and assert convergence * pass lint checks * rename * fix-reset-params * add time penalty * _get_measure_vals always returns something * fix tests * unused import * single env, fix double step * move LocalEnvManager to ml-agents-envs * move and rename EnvManager * remove obsolete docstring and method * clean up
* Don't 0 value bootstrap for GAIL and Curiosity * Add gradient penalties to GAN to help with stability * Add gail_config.yaml with GAIL examples * Cleaned up trainer_config.yaml and unnecessary gammas * Documentation updates * Code cleanup
* Removes unused SubprocessEnvManager import in trainer_controller * Removes unused `steps` argument to `TrainerController._save_model` * Consolidates unnecessary branching for curricula in `TrainerController.advance` * Moves `reward_buffer` into `TFPolicy` from `PPOPolicy` and adds `BCTrainer` support so that we don't have a broken interface / undefined behavior when BCTrainer is used with curricula.
* 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
Bringing bucket of temp memory allocation optimizations: * switched to Barracuda backed tensor across the board, helps to leverage allocators and reuse of the internal buffers * added Barracuda 0.2.4 release, which bring another set of temp memory allocation fixes
refactor vis_encoder_type and add to doc
* fix azure link * fix imitation learning links
…2258) Banana Collectors: Length of laser and agent scale Bouncer: Size of the banana
Pushblock: dynamic_friction, static_friction, block_drag, block_scale Reacher: Gravity, non-linear goal movement Walker: Gravity, torso mass
* profiling docs * clean up debug option, move csv info * Imitation Learning -> Behavioral Cloning
* Add Sampler and SamplerManager * Enable resampling of reset parameters during training * Documentation for Sampler and example YAML configuration file
* Tick versions of gym, ml-agents, ml-agents-envs * Tick communication API to 9
* Removed obsolete 'TestDstWrongShape' test as it does not reflect how Barracuda tensors work * Added proper test cleanup, to avoid warning messages from finalizer thread.
* Fix naming conventions for consistency * Add generalization link to ML-Agents Overview * Add generalization to main Readme * Include types of samplers available for use
* Removed obsolete 'TestDstWrongShape' test as it does not reflect how Barracuda tensors work * Added proper test cleanup, to avoid warning messages from finalizer thread. * Hotfix for recurrent + continous action nets in ML Agents
* add kor ver of README.md and empty docs, images * add Installation.md translated to korean * Fixed main readme docs and move all the English documents in the docs folder * modify contents of 'Installation.md' and add kr version 'Installation-Windows.md'(not completed) with related image * completed 1st translation of 'Installation-Windows.md' and added related images for korean docs * add kr version 'Using-Docker.md'(not completed) * translate Training-PPO.md to Korean * Change word about epsilon in Training-PPO.md * Fix Training PPO about epsilon * completed korean translation of 'Using-Docker.md' * Training Imitation Learning translation to Korean is finished! Also information about the translators are added * modified all 'blogs.unity3d.com/' to 'blogs.unity3d.com/kr' * removed all non-translated doc * add translator information
* Included explicit version # for ZN * added explicit version for KR docs * minor fix in installation doc * Consistency with numbers for reset parameters * Removed extra verbiage. minor consistency * minor consistency * Cleaned up IL language * moved parameter sampling above in list * Cleaned up language in Env Parameter sampling * Cleaned up migrating content * updated consistency of Reset Parameter Sampling * Rename Training-Generalization-Learning.md to Training-Generalization-Reinforcement-Learning-Agents.md * Updated doc link for generalization * Rename Training-Generalization-Reinforcement-Learning-Agents.md to Training-Generalized-Reinforcement-Learning-Agents.md * Re-wrote the intro paragraph for generalization * add titles, cleaned up language for reset params * Update Training-Generalized-Reinforcement-Learning-Agents.md * cleanup of generalization doc * More cleanup in generalization * Fixed title * Clean up included sampler type section * cleaned up defining new sampler type in generalization * cleaned up training section of generalization * final cleanup for generalization * Clean up of Training w Imitation Learning doc * updated link for generalization, reordered * consistency fix * cleaned up training ml agents doc * Update and rename Profiling.md to Profiling-Python.md * Updated Python profiling link * minor clean up in profiling doc * Rename Training-BehavioralCloning.md to Training-Behavioral-Cloning.md * Updated link to BC * Rename Training-RewardSignals.md to Reward-Signals.md * fix reward links to new * cleaned up reward signal language * fixed broken links to reward signals * consistency fix * Updated readme with generalization * Added example for GAIL reward signal * minor fixes and consistency to Reward Signals * referencing GAIL in the recording demonstration * consistency * fixed desc of bc and gail * comment fix * comments fix * Fix broken links * Fix grammar in Overview for IL * Add optional params to reward signals comment to GAIL
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).
|
|
harperj
approved these changes
Aug 1, 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.
No description provided.