63 Commits

Author SHA1 Message Date
Dmitry Vinnik 041c220b75 Remove Support Ukraine banner from ReAgent README and docs
Summary: Remove the Support Ukraine banner badge from the ReAgent open source project README and docs index files.

Reviewed By: CamiWilliams

Differential Revision: D96484191

fbshipit-source-id: 221fb8289f9db97381b4edb1b0e79a34d77bf2d4
2026-03-15 14:56:54 -07:00
Markus Obendrauf c53a595aa0 Fix typo Meta Platform -> Meta Platforms
Summary: Fix this typo inside copyright headers as it was causing our First Party detection to fail (see also D60900772)

Reviewed By: ktsiam

Differential Revision: D60902684

fbshipit-source-id: 20e13461af159d9419a75371ba965b8825e7f1c2
2024-08-12 08:45:58 -07:00
Michael Brandow 801f4ca0fa Delete RLTimelineOperator and RLExtractStateOperator
Summary:
no execution: https://fburl.com/daiquery/gk2sargj
no references: https://fburl.com/code/otg0rfbm

Reviewed By: koronthaly

Differential Revision: D52003864

fbshipit-source-id: e29f6ee2d9f10c1e7e0bd15d2d2559e8097dc399
2023-12-16 09:06:59 -08:00
Dmitry Vinnik ed087bf205 docs: add GH button in support of Ukraine (#613)
Summary:
Our mission at [Meta Open Source](https://opensource.facebook.com/) is to empower communities through open source, and we believe that it means building a welcoming and safe environment for all. As a part of this work, we are adding this banner in support for Ukraine during this crisis.

Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/613

Reviewed By: alexnikulkov

Differential Revision: D34630775

Pulled By: dmitryvinn-fb

fbshipit-source-id: 7108199313663725759377fe0972e59e9ae2cb22
2022-03-04 11:34:57 -08:00
Zhengxing Chen 31d25fb393 Update README.md
Summary: We have updated fbcode/reagent/oss/docs/index.rst in D32583915. Now, we need to also update fbcode/reagent/oss/README.md

Reviewed By: gji1

Differential Revision: D32860084

fbshipit-source-id: 7add052a1c39051cd786aa3df8ba413e1e477fc8
2021-12-04 21:57:45 -08:00
Zhengxing Chen 11073440e3 Fix more integration tests (#587)
Summary:
Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/587

The goal of this diff is to fix all integration tests except sparse_dqn ones, which needs more understanding.

Reviewed By: alexnikulkov

Differential Revision: D32589825

fbshipit-source-id: 0394dfd0c2a59a77a1957e5daa172ddb2c142657
2021-11-23 23:45:00 -08:00
Zhengxing Chen 01cc5e72f8 Fix documents
Summary: Follow the instructions in T66611582. Now the only remaining problem is that headers must include copyright.

Reviewed By: alexnikulkov

Differential Revision: D32583915

fbshipit-source-id: 13d390d756825c5e91e7801bf0dc4efec9b8b1f7
2021-11-23 23:45:00 -08:00
Alex Nikulkov 05cec23092 update Java version (#580)
Summary:
Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/580

The Java version that we were using in OSS (8.0.272.hs-adpt) seems to have been removed from sdkman
See https://app.circleci.com/pipelines/github/facebookresearch/ReAgent/2142/workflows/fc99db2e-7b69-4331-abb8-ea798aa13ec4/jobs/18221
The closest available version is 8.0.292.hs-adpt

Reviewed By: czxttkl

Differential Revision: D32509203

fbshipit-source-id: df6349619d9d0d46034833ffe667f90656d0e3ca
2021-11-18 10:15:48 -08:00
Zhengxing Chen ce3d74f7fc Update ReAgent docs (#577)
Summary:
Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/577

Update module lists following https://fb.quip.com/lEbxAN6UzLrS#UUGACAIIXSi

Reviewed By: alexnikulkov

Differential Revision: D32345725

fbshipit-source-id: fef624a759026ea7727159e22433129466bab399
2021-11-11 10:01:55 -08:00
Zhengxing Chen cae245749a Upgrade ReAgent to use Python 3.8 (#415)
Summary:
Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/415

Currently, we have some test failures (https://app.circleci.com/pipelines/github/facebookresearch/ReAgent/1460/workflows/ecc21254-779b-4a89-a40d-ea317e839d96/jobs/8655) because we miss some latest features.

Reviewed By: MisterTea

Differential Revision: D26977836

fbshipit-source-id: 9243d194ddf5c62895c9f1369830309c379fd7dd
2021-06-09 19:41:41 -07:00
Jason Gauci 39385e8d83 Tune SAC and CRR Models. Initial support for batch gym training (#470)
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/470

Reviewed By: czxttkl

Differential Revision: D28093192

fbshipit-source-id: 6b260c3e8d49c8b302e40066e2be49a0bfe96688
2021-05-18 09:27:48 -07:00
Jason Gauci a51f3cef9b move use_gpu out of model manager (#447)
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/447

Reviewed By: czxttkl

Differential Revision: D26627900

fbshipit-source-id: 7be325fada7819f011092726d1cd29fb5483d599
2021-04-23 14:50:57 -07:00
Jason Gauci 7d04310bd8 Move data fetcher out of workflow (#445)
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/445

Reviewed By: kaiwenw

Differential Revision: D27303639

fbshipit-source-id: 1c8f105a90aa929c8fecae12aa3191a0a8ed0008
2021-04-07 16:17:58 -07:00
Zhengxing Chen f08856a110 Back out recent refactor
Summary:
Need more tests before landing the refactor diffs: D22702504 (https://github.com/facebookresearch/ReAgent/commit/1b470c489d19c33beab88b8ea2e79843d4d31f28), D23123762 (https://github.com/facebookresearch/ReAgent/commit/76829287265bc39f879f3bc1d946a1374c5e1141), D23124179 (https://github.com/facebookresearch/ReAgent/commit/b28f84aa013be00194508f52498160592cb37e9d), D23219012 (https://github.com/facebookresearch/ReAgent/commit/e404c5772ea4118105c2eb136ca96ad5ca8e01db)

Back out to a version based on D23155753.

Check our team diff history: https://fburl.com/diffs/ppsgazgj

Reviewed By: kittipatv

Differential Revision: D23270626

fbshipit-source-id: 14653066bb3924a987a54650a51241895b321c8e
2020-08-21 15:58:02 -07:00
Jason Gauci 57a6da13f3 Refactor & Remove Page Handler (#299)
Summary:
Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/299

This diff accomplishes several items:
1. Remove PageHandler and consolidate all training functions into one function, using polymorphism to handle model-specific logic
2. Make BatchRunner the sole place where FB vs. OSS context is decided (by choosing FbBatchRunner or OssBatchRunner)
3. Transform ModelManager into a stateless provider.
4. With the exception of model manager, remove all duplicate classes by creating oss & internal versions and using polymorphism, or moving out of workflow/* entirely
5. Replace signals-and-slots API with interfaces
6. Create a DataFetcher class, unifying the APIs to query data on OSS and FB.

Reviewed By: kaiwenw

Differential Revision: D22702504

fbshipit-source-id: 3eb8e93144ca12ac650a4fafc875e29d8ade89e3
2020-08-17 15:13:03 -07:00
Kaiwen Wang 3029344708 Upgrade java version (#301)
Summary:
Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/301

sdk again deprecated previous version..

Reviewed By: MisterTea

Differential Revision: D22912312

fbshipit-source-id: 028fc8a7951b980528e5dda55cc0a34d49ed5b3e
2020-08-04 09:24:16 -07:00
Kaiwen Wang b023fd9d9d Fix java installation, circleci
Reviewed By: czxttkl

Differential Revision: D22649731

fbshipit-source-id: ea72f6792aee64efa331b27126a52cf2e04c5dfd
2020-07-21 13:29:50 -07:00
Stanislau Hlebik 5af0e9015e remediation of S205607
fbshipit-source-id: 798decc90db4f13770e97cdce3c0df7d5421b2a3
2020-07-17 17:07:23 -07:00
Stanislau Hlebik 1114c94e12 remediation of S205607
fbshipit-source-id: 5113fe0c527595e4227ff827253b7414abbdf7ac
2020-07-17 17:07:23 -07:00
Kai Wen Wang 3849d90445 nightly torch to support sparse features + fix a few bugs (#287)
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/287

Reviewed By: czxttkl

Differential Revision: D22473605

Pulled By: kaiwenw

fbshipit-source-id: 65e6b6e531c296e13198f4be12c6003370725e57
2020-07-10 15:48:08 -07:00
Kaiwen Wang be41a8854b Publish torchscript directly with FeedPredictor publisher
Reviewed By: kittipatv

Differential Revision: D22002221

fbshipit-source-id: d9c8601d81963938348e612c109a37fe4a2239aa
2020-06-29 15:03:49 -07:00
Kaiwen Wang 53fa77b71e Remove XGBoost
Summary: this class not used anywhere

Reviewed By: kittipatv

Differential Revision: D22105436

fbshipit-source-id: 4948d2813e7be1369958ddbb6bd8a7ca212ad645
2020-06-18 15:44:38 -07:00
Kaiwen Wang ed2d30ba33 Convert more optimizers to use new registry
Summary:
- Convert rest of models to use new registry, deprecating RLTrainer methods like set_optimizer, get_optimizer
- make TrainerParameters with make_config_class

Reviewed By: kittipatv

Differential Revision: D21759010

fbshipit-source-id: b18e72f149670371c2784edc19bb9da0337b0308
2020-06-03 15:05:27 -07:00
Kaiwen Wang b227a7efe0 Update CB RASP tutorial (#270)
Summary:
Updated CB RASP tutorial to use new OSS workflow.
Introduce FileSystemPublisher, a key-value database with tinydb, an OSS version of predictor. This way, after training the path to torchscript can be uploaded, and during evaluation it can be read.

Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/270

Reviewed By: MisterTea

Differential Revision: D21689872

fbshipit-source-id: e8d510fe895dcb33d41464e026af842e31366f87
2020-05-27 22:17:21 -07:00
Kittipat Virochsiri bb88559350 Simplifying model API
Summary:
- Delete SingleQValue and AllActionQValues; returns tensor directly
- CategoricalDQN is now taking a ModelBase which returns 3-D tensor (batch_size, num_actions, num_atoms)
- FullyConnectedDQN's constructor has one more argument, num_atoms, which default to None. When it's not None, returns 3-D tensor like above
- DuelingQNetwork takes 3 sub networks: shared_network, value_network, advantage_network. The parametric version is split out to ParametricDuelingQNetwork for better readability.
- Introduces a subclass of Sequential conforming to ModelBase API. `input_prototype()` returns the value from the first module.

Reviewed By: czxttkl

Differential Revision: D21336534

fbshipit-source-id: 629c688b0de4754effb30cd61f4a6da3cca021ab
2020-05-07 15:09:36 -07:00
Kai Wen Wang 1e5d315485 update docs (#252)
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/252

Reviewed By: kittipatv

Differential Revision: D21395945

Pulled By: kaiwenw

fbshipit-source-id: de7a78d7a806c2a25da33cc9c20291b702d7fc2d
2020-05-07 12:20:55 -07:00
Kai Wen Wang 4d07dd7bf2 fix gpu test (#238)
Summary:
Use cuda10.1 since circleCI machine cannot support cuda10.2
Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/238

Reviewed By: kittipatv

Differential Revision: D21169251

Pulled By: kaiwenw

fbshipit-source-id: 5d55ccb2c952149d08fbf129c1afb7bdfc3cf03f
2020-04-21 18:14:08 -07:00
Kittipat Virochsiri d9bbcfafc2 Fix CI (#230)
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/230

Reviewed By: kaiwenw

Differential Revision: D21025113

Pulled By: kittipatv

fbshipit-source-id: 9e7c5b514ea1c2ad72c7f6da53d71e2d8f1d5604
2020-04-14 14:53:23 -07:00
Kittipat Virochsiri 1daa98effa Simplify CI setup (#225)
Summary:
No need to build custom docker image anymore.

- Use sdkman to install compilers for Spark app
- Use miniconda to install build deps for RASP

Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/225

Reviewed By: MisterTea

Differential Revision: D20974491

Pulled By: kittipatv

fbshipit-source-id: 680ab3f60c6c63aea5854f99242243b5f1d348bc
2020-04-10 19:44:01 -07:00
Jason Gauci 6d906571a9 Rebase exprtk, handle API change in pytorch, add libbtorch to cuda dockerfile (#210)
Summary:
Fixes https://github.com/facebookresearch/ReAgent/issues/201 #208
Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/210

Reviewed By: czxttkl

Differential Revision: D19724659

Pulled By: MisterTea

fbshipit-source-id: a83535221ef603b2ba28a66aea0e837ed0ac8229
2020-02-10 14:49:01 -08:00
Zhengxing Chen fed370d1b9 Fix usage example (#196)
Summary:
Fix the usage example such that it obtains a reasonable policy.

Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/196

Test Plan:
Imported from GitHub, without a `Test Plan:` line.

Existing tests pass.
Manually ran `run_end_to_end_test.sh` and it passed.

Reviewed By: kittipatv

Differential Revision: D19078228

Pulled By: czxttkl

fbshipit-source-id: d50f4fd258583635d16b087f324cd75d18931200
2019-12-29 05:14:49 -08:00
Kittipat Virochsiri 7ab6e59c17 Finally kill thrift config
Summary: We no longer use Thrift for configuration

Reviewed By: czxttkl

Differential Revision: D18242481

fbshipit-source-id: bfdfa1e7baa21be92bb51a7103d0f379dafee2b2
2019-10-31 12:28:11 -07:00
Zhengxing Chen 8ece668954 Update docs
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/178

Reviewed By: kittipatv

Differential Revision: D18165626

Pulled By: czxttkl

fbshipit-source-id: 034ed0a37924df1113c5a1332a771bd4e0aeb5bb
2019-10-28 23:15:36 -07:00
Brett Koonce d2be5b2fe3 minor spelling tweaks
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/162

Reviewed By: kittipatv

Differential Revision: D17921494

Pulled By: MisterTea

fbshipit-source-id: 6c5d4d90e5f36ae05ff9fcb387611c995dd110ac
2019-10-23 11:07:43 -07:00
Kittipat Virochsiri 3568219773 minor doc fix
Summary: Missing a new line causing the block not to render

Reviewed By: czxttkl

Differential Revision: D17999728

fbshipit-source-id: 20af5affbbe8b0bd54c7261d424cf9b033bb5e3d
2019-10-17 21:15:03 -07:00
Kittipat Virochsiri 492b70b749 CI instructions
Summary: Add a page for CI instructions

Reviewed By: czxttkl

Differential Revision: D17983742

fbshipit-source-id: 31479a349310a55844cea7ea97629fcd96d5b1b6
2019-10-17 17:39:06 -07:00
Zhengxing Chen 338c374a35 Horizon -> ReAgent in subpages
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/173

Reviewed By: kittipatv

Differential Revision: D17950105

Pulled By: czxttkl

fbshipit-source-id: 10005fd416697e926e231e7d13cd3db29d28c602
2019-10-16 01:01:05 -07:00
Jason Gauci 9a4c719643 minor doc fixes
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/171

Reviewed By: czxttkl

Differential Revision: D17948650

Pulled By: MisterTea

fbshipit-source-id: ce3a891eef4293b977319e1b21e6c019299dfac7
2019-10-15 23:33:08 -07:00
Zhengxing Chen 747011f633 update logo
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/166

Reviewed By: MisterTea

Differential Revision: D17933761

Pulled By: czxttkl

fbshipit-source-id: d445a862c22d143d83111e510474f52dfa0f9440
2019-10-15 22:32:35 -07:00
Jason Gauci f3a0c30321 Rasp bag of fixes
Summary: Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/165

Reviewed By: ppuliu

Differential Revision: D17933739

Pulled By: MisterTea

fbshipit-source-id: 3dcd8b10cc4b8b9a62e9889278475c1f306fd4a0
2019-10-15 17:51:27 -07:00
Zhengxing Chen 24961c1e5f update sphinx docs file (#163)
Summary:
Will update gh-pages branch in another diff.
Pull Request resolved: https://github.com/facebookresearch/ReAgent/pull/163

Reviewed By: MisterTea, kittipatv

Differential Revision: D17924969

Pulled By: czxttkl

fbshipit-source-id: b63dafa0b514b908ecb8ad605416ecbc90ef03b3
2019-10-14 23:23:09 -07:00
Zhengxing Chen 539d22cd83 update sphinx (#146)
Summary:
Update several things so that sphinx compiled successfully:
conf.py (add onnx in autodoc_mock_imports and add Horizon root to sys.path)
ml/rl/caffe_utils.py (update __getattr__ such that sphnix wouldn't throw exception)
ml/rl/tensorboardX.py (update __getattr__ such that sphnix wouldn't throw exception)
Pull Request resolved: https://github.com/facebookresearch/Horizon/pull/146

Test Plan: Wait for all integration tests and unit tests pass

Reviewed By: kittipatv

Differential Revision: D16243745

Pulled By: czxttkl

fbshipit-source-id: e3b8af37ec520bde44a4a59379341bceaa981070
2019-07-18 16:03:39 -07:00
Jason Gauci 2a548989f9 GymPredictor -> OnPolicyPredictor. Cleanup
Reviewed By: kittipatv

Differential Revision: D15895899

fbshipit-source-id: 8d4c84ce01b626af07b24f2a3d62f178cf393b83
2019-06-22 18:05:59 -07:00
Edoardo Conti 95565d6c86 Minor OS fixes (#131)
Summary:
Fix broken test in open source master

Pull Request resolved: https://github.com/facebookresearch/Horizon/pull/131

Reviewed By: kittipatv

Differential Revision: D15399272

Pulled By: econti

fbshipit-source-id: f89520bddbf5a5ac87ff86b3f6d9b550d43e5a60
2019-05-17 13:58:44 -07:00
Jason Gauci a3bc5837dc Distributed training docs
Summary: Pull Request resolved: https://github.com/facebookresearch/Horizon/pull/120

Reviewed By: econti

Differential Revision: D15031373

Pulled By: MisterTea

fbshipit-source-id: f397e74a90cecb6a6118b35b557e81bf23749d52
2019-04-22 17:40:27 -07:00
Jason Gauci 9423705a6c Add sphinx documentation. Convert markdown files to rst.
Summary: Pull Request resolved: https://github.com/facebookresearch/Horizon/pull/119

Reviewed By: kittipatv

Differential Revision: D14992371

Pulled By: MisterTea

fbshipit-source-id: 9ebe007009be3a1e22556724254da710dd7a5d3e
2019-04-19 10:42:57 -07:00
Jason Gauci 05cf7caeb1 Docker improvements
Summary: Pull Request resolved: https://github.com/facebookresearch/Horizon/pull/105

Reviewed By: kittipatv

Differential Revision: D14320299

Pulled By: MisterTea

fbshipit-source-id: a9b72ed088ecf9f16d797a5597d4322778f169b1
2019-03-05 14:52:46 -08:00
Jason Gauci a42f1dc6a2 More oss fixes
Summary: Pull Request resolved: https://github.com/facebookresearch/Horizon/pull/104

Reviewed By: econti

Differential Revision: D14260743

Pulled By: MisterTea

fbshipit-source-id: 3ce1031e5da47a44aa7e6ab98fb5239312a769aa
2019-03-01 19:53:12 -08:00
Jason Gauci 30c75bed0e Update installation & usage guide, and fix issues related to that.
Summary: Pull Request resolved: https://github.com/facebookresearch/Horizon/pull/93

Reviewed By: kittipatv, econti

Differential Revision: D13873903

Pulled By: MisterTea

fbshipit-source-id: bb75dd687f6de0e3884c841e4bdfc460c44662d3
2019-01-30 12:00:19 -08:00
Jason Gauci 2654cd769f Add eval data and clean up gym datasets
Summary: Pull Request resolved: https://github.com/facebookresearch/Horizon/pull/81

Reviewed By: kittipatv

Differential Revision: D13445814

Pulled By: MisterTea

fbshipit-source-id: f8be2e4a728562750bd32e4e2df93a6d7b03a4f7
2018-12-15 15:12:34 -08:00