update #1
Merged
update #1
Conversation
This file contains 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
Error caused by the recent upgrade of the `importlib-metadata`. 4 Oct, 2022.
* Adding new blog It is adding a new blog that summarises week 05 based on the provided materials for this week. * Update README.md * Update README.md Co-authored-by: Dmitry Nikulin <[email protected]>
* Downloading & Install `xvfb` for video game recording Fixed the error of `bash: ../xvfb: No such file or directory`, and now the videos are working on Colab and any server. * Remove incorrect comment Co-authored-by: Dmitry Nikulin <[email protected]>
Update week03: gym -> gymnasium, renew points, merge notebooks
* fix regret calculation in week5 * fix regret formula
Multiprocessing in Python works differently on Windows and on Linux. On Windows it copies the objects and in Linux it doesn't. As a result, some code that works fine on Linux may not work on Windows. E.g. in our A2C homework we use lambda functions. Lambda functions are not serializable, so object copying during multiprocessing would fail on Windows. As for MacOS, it can behave like Linux or like Windows depending on settings. In this commit I added an instruction that will make the multiprocessing behave like Linux
* Support gym 0.26 There are changes in gym API between 0.25 and 0.26 These changes break backward compatibility. In this commit we updated the code of week6 seminar to use gym 0.26 What is changed: - env initializer; - env.render; - env.reset; - env.step; - video recording Note: didn't test in Colab, only locally * week6 seminar: Uppdate video dependencies for Colab * week6 seminar: minor fix in installing
Co-authored-by: Dmitry Dryomov <[email protected]>
[Week01] Migrate to gymnasium
…ymnaasium in description" This reverts commit 59c7fa6.
This reverts commit fe79654.
[Week04] Migrate to gymnasium
The link in README.md and the ipynb notebook was pointing to an unavailable resource, leading to a broken user experience. This commit resolves the issue by updating the link to a valid URL, ensuring users can access the intended resource without any problems. Changes Made: - Fixed broken link in README.md - Fixed broken link in ipynb notebook Fixes #529
* migrate to gymnasium * small fix of env.reset()
* migrate to gymnasium * minor fixes * use get_wrapper_attr to get writer * return SummariesBase and NumpySummaries, refactor summaries classes * torch.long -> torch.int64 * swap width and height in ImagePreprocessing, fix order in SwapImageAxes * fix SwapImageAxes description * fix cv2.resize arguments
* migrate mcts to gymnasium * change name * rm reset() arguments * delete redundant import, add comments
* add gymnasium interfaces to py files * migrate trpo to gymnasium * migrate ppo to gymnasium * migrate continuous control hw to gymnasium * fix super() * fix code * fix typo in hw-continuous-control_pytorch.ipynb * fix termination and truncation processing * return done
* reset = terminated or truncated * reset = terminated or truncated
Remove `graph_size` argument from plot_graph()
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.