A PyTorch implementation of DeepMind's MCTSnet
faameunier, updated
🕥
2022-12-08 04:51:24
This is a work in progress. Any ideas welcomed !
Installation
To install all dependancies
pip install -r requirements.txt
To install Sokoban environment
git clone https://github.com/mpSchrader/gym-sokoban.git
cd gym-sokoban
pip install -e .
Run and test
See main.ipynb for details.
Description
This implementation tries to follow "Learning to search with MCTSnets" (Guez et al.) [1] as closely as possible. All mentioned networks are available in MCTSnet/models/. We focused on a simple random policy as a first step and the approximate computation for the policy gradient is not implemented. This should however provide good results according to the authors.
MCTSnet/models/MCTSnet.py implements all the search logic.
The code tends to be quite general and should easily be adapted for any environment (we tried to use an interface as close to gym as possible).
MCTSnet/trainer.py provides an easy way to train, test and play games. Two games were tested: - the Sokoban, as per the original article - the MouseGame, a simple game were a mouse need to eat the cheese and avoid poison
The algorithm has proven to converge on the mousegame, however even after 15hours of training the MCTSnet performance is poor. Additionnal testing is required.
For a detailed description please check https://github.com/faameunier/MCTSnet/blob/master/RL_Manuscript.pdf
References
[1] Arthur Guez, Theophane Weber, Ioannis Antonoglou, Karen Simonyan, Oriol Vinyals, Daan Wierstra, Remi Munos, and David Silver. Learning to search with mctsnets. CoRR, abs/1802.04697, 2018.
Issues
Bump certifi from 2019.3.9 to 2022.12.7
opened on 2022-12-08 04:51:23 by dependabot[bot]Bumps certifi from 2019.3.9 to 2022.12.7.
Commits
9e9e8402022.12.07b81bdb22022.09.24939a28f2022.09.14aca828a2022.06.15.2de0eae1Only use importlib.resources's new files() / Traversable API on Python ≥3.11 ...b8eb5e92022.06.15.147fb7abFix deprecation warning on Python 3.11 (#199)b0b48e0fixes #198 -- update link in license9d514b42022.06.154151e88Add py.typed to MANIFEST.in to package in sdist (#196)- Additional commits viewable in compare view
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.
Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/faameunier/MCTSnet/network/alerts).
Bump pillow from 5.4.1 to 9.3.0
opened on 2022-11-22 03:27:43 by dependabot[bot]Bumps pillow from 5.4.1 to 9.3.0.
Release notes
Sourced from pillow's releases.
9.3.0
https://pillow.readthedocs.io/en/stable/releasenotes/9.3.0.html
Changes
- Initialize libtiff buffer when saving #6699 [
@radarhere]- Limit SAMPLESPERPIXEL to avoid runtime DOS #6700 [
@wiredfool]- Inline fname2char to fix memory leak #6329 [
@nulano]- Fix memory leaks related to text features #6330 [
@nulano]- Use double quotes for version check on old CPython on Windows #6695 [
@hugovk]- GHA: replace deprecated set-output command with GITHUB_OUTPUT file #6697 [
@nulano]- Remove backup implementation of Round for Windows platforms #6693 [
@cgohlke]- Upload fribidi.dll to GitHub Actions #6532 [
@nulano]- Fixed set_variation_by_name offset #6445 [
@radarhere]- Windows build improvements #6562 [
@nulano]- Fix malloc in _imagingft.c:font_setvaraxes #6690 [
@cgohlke]- Only use ASCII characters in C source file #6691 [
@cgohlke]- Release Python GIL when converting images using matrix operations #6418 [
@hmaarrfk]- Added ExifTags enums #6630 [
@radarhere]- Do not modify previous frame when calculating delta in PNG #6683 [
@radarhere]- Added support for reading BMP images with RLE4 compression #6674 [
@npjg]- Decode JPEG compressed BLP1 data in original mode #6678 [
@radarhere]- pylint warnings #6659 [
@marksmayo]- Added GPS TIFF tag info #6661 [
@radarhere]- Added conversion between RGB/RGBA/RGBX and LAB #6647 [
@radarhere]- Do not attempt normalization if mode is already normal #6644 [
@radarhere]- Fixed seeking to an L frame in a GIF #6576 [
@radarhere]- Consider all frames when selecting mode for PNG save_all #6610 [
@radarhere]- Don't reassign crc on ChunkStream close #6627 [
@radarhere]- Raise a warning if NumPy failed to raise an error during conversion #6594 [
@radarhere]- Only read a maximum of 100 bytes at a time in IMT header #6623 [
@radarhere]- Show all frames in ImageShow #6611 [
@radarhere]- Allow FLI palette chunk to not be first #6626 [
@radarhere]- If first GIF frame has transparency for RGB_ALWAYS loading strategy, use RGBA mode #6592 [
@radarhere]- Round box position to integer when pasting embedded color #6517 [
@radarhere]- Removed EXIF prefix when saving WebP #6582 [
@radarhere]- Pad IM palette to 768 bytes when saving #6579 [
@radarhere]- Added DDS BC6H reading #6449 [
@ShadelessFox]- Added support for opening WhiteIsZero 16-bit integer TIFF images #6642 [
@JayWiz]- Raise an error when allocating translucent color to RGB palette #6654 [
@jsbueno]- Moved mode check outside of loops #6650 [
@radarhere]- Added reading of TIFF child images #6569 [
@radarhere]- Improved ImageOps palette handling #6596 [
@PososikTeam]- Defer parsing of palette into colors #6567 [
@radarhere]- Apply transparency to P images in ImageTk.PhotoImage #6559 [
@radarhere]- Use rounding in ImageOps contain() and pad() #6522 [
@bibinhashley]- Fixed GIF remapping to palette with duplicate entries #6548 [
@radarhere]- Allow remap_palette() to return an image with less than 256 palette entries #6543 [
@radarhere]- Corrected BMP and TGA palette size when saving #6500 [
@radarhere]
... (truncated)
Changelog
Sourced from pillow's changelog.
9.3.0 (2022-10-29)
Limit SAMPLESPERPIXEL to avoid runtime DOS #6700 [wiredfool]
Initialize libtiff buffer when saving #6699 [radarhere]
Inline fname2char to fix memory leak #6329 [nulano]
Fix memory leaks related to text features #6330 [nulano]
Use double quotes for version check on old CPython on Windows #6695 [hugovk]
Remove backup implementation of Round for Windows platforms #6693 [cgohlke]
Fixed set_variation_by_name offset #6445 [radarhere]
Fix malloc in _imagingft.c:font_setvaraxes #6690 [cgohlke]
Release Python GIL when converting images using matrix operations #6418 [hmaarrfk]
Added ExifTags enums #6630 [radarhere]
Do not modify previous frame when calculating delta in PNG #6683 [radarhere]
Added support for reading BMP images with RLE4 compression #6674 [npjg, radarhere]
Decode JPEG compressed BLP1 data in original mode #6678 [radarhere]
Added GPS TIFF tag info #6661 [radarhere]
Added conversion between RGB/RGBA/RGBX and LAB #6647 [radarhere]
Do not attempt normalization if mode is already normal #6644 [radarhere]
... (truncated)
Commits
d594f4cUpdate CHANGES.rst [ci skip]909dc649.3.0 version bump1a51ce7Merge pull request #6699 from hugovk/security-libtiff_buffer2444cddMerge pull request #6700 from hugovk/security-samples_per_pixel-sec744f455Added release notes0846bfaAdd to release notes799a6a0Fix linting00b25fdHide UserWarning in logs05b175eTighter test case13f2c5aPrevent DOS with large SAMPLESPERPIXEL in Tiff IFD- Additional commits viewable in compare view
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.
Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/faameunier/MCTSnet/network/alerts).
Bump nbconvert from 5.4.1 to 6.5.1
opened on 2022-08-23 17:32:51 by dependabot[bot]Bumps nbconvert from 5.4.1 to 6.5.1.
Release notes
Sourced from nbconvert's releases.
Release 6.5.1
No release notes provided.
6.5.0
What's Changed
- Drop dependency on testpath. by
@anntzerin jupyter/nbconvert#1723- Adopt pre-commit by
@blink1073in jupyter/nbconvert#1744- Add pytest settings and handle warnings by
@blink1073in jupyter/nbconvert#1745- Apply Autoformatters by
@blink1073in jupyter/nbconvert#1746- Add git-blame-ignore-revs by
@blink1073in jupyter/nbconvert#1748- Update flake8 config by
@blink1073in jupyter/nbconvert#1749- support bleach 5, add packaging and tinycss2 dependencies by
@bollwyvlin jupyter/nbconvert#1755- [pre-commit.ci] pre-commit autoupdate by
@pre-commit-ciin jupyter/nbconvert#1752- update cli example by
@leahecolein jupyter/nbconvert#1753- Clean up pre-commit by
@blink1073in jupyter/nbconvert#1757- Clean up workflows by
@blink1073in jupyter/nbconvert#1750New Contributors
@pre-commit-cimade their first contribution in jupyter/nbconvert#1752Full Changelog: https://github.com/jupyter/nbconvert/compare/6.4.5...6.5
6.4.3
What's Changed
- Add section to
customizingshowing how to use template inheritance by@stefanvin jupyter/nbconvert#1719- Remove ipython genutils by
@rgs258in jupyter/nbconvert#1727- Update changelog for 6.4.3 by
@blink1073in jupyter/nbconvert#1728New Contributors
@stefanvmade their first contribution in jupyter/nbconvert#1719@rgs258made their first contribution in jupyter/nbconvert#1727Full Changelog: https://github.com/jupyter/nbconvert/compare/6.4.2...6.4.3
6.4.0
What's Changed
- Optionally speed up validation by
@gwincr11in jupyter/nbconvert#1672- Adding missing div compared to JupyterLab DOM structure by
@SylvainCorlayin jupyter/nbconvert#1678- Allow passing extra args to code highlighter by
@yuvipandain jupyter/nbconvert#1683- Prevent page breaks in outputs when printing by
@SylvainCorlayin jupyter/nbconvert#1679- Add collapsers to template by
@SylvainCorlayin jupyter/nbconvert#1689- Fix recent pandoc latex tables by adding calc and array (#1536, #1566) by
@cgevansin jupyter/nbconvert#1686- Add an invalid notebook error by
@gwincr11in jupyter/nbconvert#1675- Fix typos in execute.py by
@TylerAnderson22in jupyter/nbconvert#1692- Modernize latex greek math handling (partially fixes #1673) by
@cgevansin jupyter/nbconvert#1687- Fix use of deprecated API and update test matrix by
@blink1073in jupyter/nbconvert#1696- Update nbconvert_library.ipynb by
@letterphilein jupyter/nbconvert#1695- Changelog for 6.4 by
@blink1073in jupyter/nbconvert#1697New Contributors
... (truncated)
Commits
7471b75Release 6.5.1c1943e0Fix pre-commit8685e93Fix tests0abf290Run black and prettier418d545Run test on 6.x branchbef65d7Convert input to string prior to escape HTML0818628Check input type before escapingb206470GHSL-2021-1017, GHSL-2021-1020, GHSL-2021-1021a03cbb8GHSL-2021-1026, GHSL-2021-102548fe71eGHSL-2021-1024- Additional commits viewable in compare view
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.
Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/faameunier/MCTSnet/network/alerts).
Bump mistune from 0.8.4 to 2.0.3
opened on 2022-07-29 22:51:24 by dependabot[bot]Bumps mistune from 0.8.4 to 2.0.3.
Release notes
Sourced from mistune's releases.
Version 2.0.2
Fix
escape_urlvia lepture/mistune#295Version 2.0.1
Fix XSS for image link syntax.
Version 2.0.0
First release of Mistune v2.
Version 2.0.0 RC1
In this release, we have a Security Fix for harmful links.
Version 2.0.0 Alpha 1
This is the first release of v2. An alpha version for users to have a preview of the new mistune.
Changelog
Sourced from mistune's changelog.
Changelog
Here is the full history of mistune v2.
Version 2.0.4
Released on Jul 15, 2022
- Fix
urlplugin in<a>tag- Fix
*formattingVersion 2.0.3
Released on Jun 27, 2022
- Fix
tableplugin- Security fix for CVE-2022-34749
Version 2.0.2
Released on Jan 14, 2022Fix
escape_urlVersion 2.0.1
Released on Dec 30, 2021
XSS fix for image link syntax.
Version 2.0.0
Released on Dec 5, 2021This is the first non-alpha release of mistune v2.
Version 2.0.0rc1
Released on Feb 16, 2021
Version 2.0.0a6
</tr></table>
... (truncated)
Commits
3f422f1Version bump 2.0.3a6d4321Fix asteris emphasis regex CVE-2022-347495638e46Merge pull request #307 from jieter/patch-10eba471Fix typo in guide.rst61e9337Fix table plugin76dec68Add documentation for renderer heading when TOC enabled799cd11Version bump 2.0.2babb0cfMerge pull request #295 from dairiki/bug.escape_urlfc2cd53Make mistune.util.escape_url less aggressive3e8d352Version bump 2.0.1- Additional commits viewable in compare view
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.
Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/faameunier/MCTSnet/network/alerts).
Bump numpy from 1.16.2 to 1.22.0
opened on 2022-06-21 21:45:26 by dependabot[bot]Bumps numpy from 1.16.2 to 1.22.0.
Release notes
Sourced from numpy's releases.
v1.22.0
NumPy 1.22.0 Release Notes
NumPy 1.22.0 is a big release featuring the work of 153 contributors spread over 609 pull requests. There have been many improvements, highlights are:
- Annotations of the main namespace are essentially complete. Upstream is a moving target, so there will likely be further improvements, but the major work is done. This is probably the most user visible enhancement in this release.
- A preliminary version of the proposed Array-API is provided. This is a step in creating a standard collection of functions that can be used across application such as CuPy and JAX.
- NumPy now has a DLPack backend. DLPack provides a common interchange format for array (tensor) data.
- New methods for
quantile,percentile, and related functions. The new methods provide a complete set of the methods commonly found in the literature.- A new configurable allocator for use by downstream projects.
These are in addition to the ongoing work to provide SIMD support for commonly used functions, improvements to F2PY, and better documentation.
The Python versions supported in this release are 3.8-3.10, Python 3.7 has been dropped. Note that 32 bit wheels are only provided for Python 3.8 and 3.9 on Windows, all other wheels are 64 bits on account of Ubuntu, Fedora, and other Linux distributions dropping 32 bit support. All 64 bit wheels are also linked with 64 bit integer OpenBLAS, which should fix the occasional problems encountered by folks using truly huge arrays.
Expired deprecations
Deprecated numeric style dtype strings have been removed
Using the strings
"Bytes0","Datetime64","Str0","Uint32", and"Uint64"as a dtype will now raise aTypeError.(gh-19539)
Expired deprecations for
loads,ndfromtxt, andmafromtxtin npyio
numpy.loadswas deprecated in v1.15, with the recommendation that users usepickle.loadsinstead.ndfromtxtandmafromtxtwere both deprecated in v1.17 - users should usenumpy.genfromtxtinstead with the appropriate value for theusemaskparameter.(gh-19615)
... (truncated)
Commits
4adc87dMerge pull request #20685 from charris/prepare-for-1.22.0-releasefd66547REL: Prepare for the NumPy 1.22.0 release.125304bwipc283859Merge pull request #20682 from charris/backport-204165399c03Merge pull request #20681 from charris/backport-20954f9c45f8Merge pull request #20680 from charris/backport-20663794b36fUpdate armccompiler.pyd93b14eUpdate test_public_api.py7662c07Update init.py311ab52Update armccompiler.py- Additional commits viewable in compare view
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.
Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/faameunier/MCTSnet/network/alerts).
Bump notebook from 5.7.8 to 6.4.12
opened on 2022-06-16 23:19:52 by dependabot[bot]Bumps notebook from 5.7.8 to 6.4.12.
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.
Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/faameunier/MCTSnet/network/alerts).
pytorch mcts deep-reinforcement-learning deep-learning reinforcement-learning deep-neural-networks sokoban-solver