release-v0.6 --> master #1494
Merged
release-v0.6 --> master #1494
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
* initial commit : Only works with PPO balance ball * Fix for recurrent * [Fix indentation error] * Fixed BC * Remove Dead code * Addressing comment : Removing dead code * Fixing the Pytest * edited comments * Removing GraphScope from the InternalBrain (#1227) * Documentation changes for removing graph scope (#1226) * Documentation changes * removed the keep checkpoint printing
I feel the previous description was misleading.
The calculation of observation vectors is faulty. The old calculation does not reflect distances to the edges and it does not only yield results between -1 and 1. Since distance calculation would have been difficult in one line, I just replaced it by the relative position of the ball (only using two vectors instead of four). I've conducted 500K-step reinforcing trainings before and after the change and got enormously improved results. Contact me for screenshots of the tensorboard or just use the debugger and do the math.
Minor textual adaptions...
Fix typos
More semantically correct description
Fix bug in observation vector calculation
Ball rotation does not feed into observation.
Ow... sorry, there was a typo.
…lace to control this (#1285)
Fixed the fix...
Fixed wrong description in 3D Ballance Ball
Put Time Horizon back into the default training config for BC
* 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 Academy * Removed refences to CoreBrain * Fix import bug * Addressed some comments * Remove useless imports * Added nice icons for the brains * Added a feature to deepcopy brain parameters between brains * Resolve drawer bug * Develop scriptable brains ball scene (#1233) * Created the Brains for the Ballance Ball Environment * Modified the Balance Ball Scene * Renamed Training Hub to Broadcast Hub * Added a comment * renamed SetToControlled to SetControlledExternally in the Learning Brain * Resolved errors in case ENABLE_TENSORFLOW is not activated * Update the BalanceBall Scene * Refactored the BrainParameters drawer * Addressed offline comments * Comments on the ResetParametersDrawer * refactired the BroadcastHubDrawer * Adding comments * Add comment on the horizontal bar * Added new comments * Refactor of the Editors * minor changes * Added documentation, Fixed a bug in the tenporary internal brain when TF# is disabled * Develop scriptable brains documentation (#1249) * Modified first docs * modified the markdown, not the images * Missing doc * Replaced Internal with Learned Brain * updated the images * Addressed some comments * Renamed Training Hub to Broadcast Hub * Forgot one file * Added new images * addressing comment * Fixed some typos * address comments on the code * addressed comments on documents * Resolving conflicts on the Learning Brain * Minor tweaks * Addressed Comments * Created a Clone method in the BrainParameters, created a new BrainParameters file, made a CumSum method * Added Unit Test
Replace ##Inference Configuration## by ##Training Configuration##
* Add link to notebook in python-api page * Use relative path * Fix line
* add make.bat for windows * fix syntax * fix commented part * fix description
…awlerDynamic (#1313) * New brains for Pyramid scene * Add reacher brains * New brains for Soccer agents * New Tennis Brains * Set prefabs correctly * New brains for bouncer * New Dynamic Crawler Brains
…rld, walljump, visualhallway, visualpushblock, visualpyramid (#1314)
* More accurate steps to use aws instance * change the // to #, change the words according to the comments
* added the note about the windows bug * made them uniform * added where the parameter is * resolved the comments * added one space
* pull/1294 from has-taiar * removed the left bracket * moved the windows link position * update the windows doc * resolved the comments, changed the pip install . to pip install -e . , added the package explanation to the Windows installation doc * Resolved the comments * add the 'the'
* split the config into two files * fixed the Training-ML-Agents.md doc * added the configs for all of the IL scenes
…offline Fix on the bc_offline_training using deep copies
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.
Use the new icons for the brains
Move done and reward to buffer from demonstration
…rsion tick the version number
* Add Gizmos folder to create new env guide
Documentation Updates
eshvk
approved these changes
Dec 14, 2018
tick the gym-unity setup.py
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.