Release v0.4 #884
Merged
Release v0.4 #884
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
No game object is named "Platform" therefore the legs never make contact with anything
* Report means instead of totals for losses. * Report absolute loss for policy.
* [Fix] Use the stored agent info instead of the previous agent info when bootstraping the value * [Bug Fix] Addressed #643 * [Added Line Break]
…r the first episode (#657)
Quick start integrated into Installation
This PR makes the following changes: * Moves clipping of continuous control model into model itself. Output is now always [-1, 1]. * Internal model values are now clipped between [-3, 3] before being rescaled to [-1, 1] for output. * This improves training performance by providing a wider range of values within which the pdf of the gaussian can fall. Output of [-1, 1] is used to be more environment-creator friendly. * Fixes issue where epsilon was erroneously being used to reconstruct old probabilities during PPO update, leading to reduced learning performance. * Introduce ScaleAction() function within python to easily rescale values from [-1, 1] to arbitrary range. * Re-train all CC models using improved algorithm. All performance levels are equal or improved. In the case of Crawler, improvement is drastic. * Update documentation appropriately. * Made miscellaneous minor code style and optimization improvements within environments.
…n-video-link added the video link
Add ignore for plugins folder
* [Cold Fix] Split the way cummulative rewards and episode length are counted The reward is appended at each step to the cummulative reward The episode count is ONLY incremented when d_t+1 is false
* Add `Walker` example environment and documentation.
* First draft of Azure support docs * Correcting links to other docs * Adding additional links and cleaning instructions * Adding references to Azure docs in other appropriate places
added video links
- Indent the section about providing actions to multiple brains to be in line with the rest of the step() docs. - Move the line about what step() returns closer to the top of the docs so it's harder to overlook. - Add a small code snippet about how to get BrainInfo belonging to a specific brain and how to get data from that BrainInfo object.
* [Refactor] Fixed line indentation * Removed the library Newtonsoft.Json from the monitor * Replaced calls to JSON converstion with manual conversion * [Modified] The Monitor now has multiple * Log methods that take different object types
* [Added Ascii art on learn.py] Note : This is by far the best feature of 0.4
Some suggestions to avoid ambiguity
Shouldn't Done(); be placed after the rewards are given?
Replaced UNITY ML AGENTS with the unity logo
* Fix BananaIL frozen agent material * [Fix] Added texture on the imitation learning scene and linked the models to the internal brains
Also made the look code into Update
…l-bugfix [Hotfix] Remove code in PushAgentBasic that presumes that there is only one brain
* Added missing declaration to docs sample code. * Added pretrained model as default graph in Internal brain of Tennis scene * Disabled PlayerBrain in Tennis by default. * Removed accidental config.
…model-fix some hack to make windows save the model when do ctrl+c
…not been trained for them (#877)
* Remove extra bouncer brain hyperparameters * Add error when using curiosity+odd
|
:+1 |
eshvk
approved these changes
Jun 16, 2018
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.