Release 0.9.2 #2469
Merged
Release 0.9.2 #2469
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
* WIP still needs tests and merging from multiprocess * cleanup gauges * add TODO for subprocesses
Merge latest fixes from release into develop
* discrete action coverage * undo change * rename test * move test file * Revert "move test file" This reverts commit 2e72b2d. * move files post merge
fix mock_brain
Add MultiGpuPPOPolicy class and command line options to run multi-GPU training
Return list instead of np array for make_mini_batch() to reduce time copying data
This change moves trainer initialization outside of TrainerController, reducing some of the constructor arguments of TrainerController and setting up the ability for trainers to be initialized in the case where a TrainerController isn't needed.
- Move common functions to trainer.py, model.pyfromppo/trainer.py, ppo/policy.pyandppo/model.py' - Introduce RLTrainer class and move most of add_experiences and some common reward signal code there. PPO and SAC will inherit from this, not so much BC Trainer. - Add methods to Buffer to enable sampling, truncating, and save/loading. - Add scoping to create encoders in model.py
Hotfix v0.9.1 - develop
Variable "model" is undefined.
…into RunSwimFlyRich-master # Conflicts: # UnitySDK/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerDynamicLearning.nn # UnitySDK/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerStaticLearning.nn
* Adds evaluate_batch to reward signals. Evaluates on minibatch rather than on BrainInfo. * Changes the way reward signal results are reported in rl_trainer so that we get the pure, unprocessed environment reward separate from the reward signals. * Moves end_episode to rl_trainer * Fixed bug with BCModule with RNN
In order for downstream packages to make use of the latest pre-release features, we can pre-release versions of our packages. For packages ending in `devN` pip will not install that package version by default. This change manually updates our package version to a development version with the idea that we can manually perform development versions with the potential for future automated / nightly dev releases.
…r-prefabs fixed broken crawler prefabs
…errors-crawler Fix NaN training errors for crawler
|
|
More flexibility on the h5py version
…gpu-doc Added the doc for multi-gpu
…-fix Fixed the flake8
chriselion
approved these changes
Aug 28, 2019
vincentpierre
approved these changes
Aug 28, 2019
| Vector3 velocityRelativeToLookRotationToTarget = targetDirMatrix.inverse.MultiplyVector(rb.velocity); | ||
| AddVectorObs(velocityRelativeToLookRotationToTarget); | ||
|
|
||
| Vector3 angularVelocityRelativeToLookRotationToTarget = targetDirMatrix.inverse.MultiplyVector(rb.angularVelocity); |
There was a problem hiding this comment.
Line too long, also, We should have a description of what targetDirMatrix.inverse does because it is not obvious.
| // Update pos to target | ||
| dirToTarget = target.position - body.position; | ||
| lookRotation = Quaternion.LookRotation(dirToTarget); | ||
| targetDirMatrix = Matrix4x4.TRS(Vector3.zero, lookRotation, Vector3.one); |
There was a problem hiding this comment.
What does TRS do ? Can we have some explanation?
There was a problem hiding this comment.
Matrix4x4.TRS creates a 4x4 matrix with Translate, Rotation, and Scale components.
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.