diff --git a/README.md b/README.md index 09ccbde..4c78131 100644 --- a/README.md +++ b/README.md @@ -9,7 +9,8 @@ [![GitHub last commit](https://img.shields.io/github/last-commit/hakuhodo-technologies/scope-rl)](https://github.com/hakuhodo-technologies/scope-rl/graphs/commit-activity) [![Documentation Status](https://readthedocs.org/projects/scope-rl/badge/?version=latest)](https://scope-rl.readthedocs.io/en/latest/) [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) -[![arXiv](https://img.shields.io/badge/arXiv-23xx.xxxxx-b31b1b.svg)](https://arxiv.org/abs/23xx.xxxxx) +[![arXiv](https://img.shields.io/badge/arXiv-2311.18206-b31b1b.svg)](https://arxiv.org/abs/2311.18206) +[![arXiv](https://img.shields.io/badge/arXiv-2311.18207-b31b1b.svg)](https://arxiv.org/abs/2311.18207)
Table of Contents (click to expand) @@ -442,14 +443,14 @@ If you use our software in your work, please cite our paper: Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation**
-[link]() (a preprint coming soon..) +[[arXiv](https://arxiv.org/abs/2311.18206)] [[slides](https://speakerdeck.com/harukakiyohara_/scope-rl)] Bibtex: ``` @article{kiyohara2023scope, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year={2023}, } ``` @@ -458,14 +459,14 @@ If you use our proposed metric "SharpeRatio@k" in your work, please cite our pap Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation**
-[link]() (a preprint coming soon..) +[[arXiv](https://arxiv.org/abs/2311.18207)] [[slides](https://speakerdeck.com/harukakiyohara_/towards-risk-return-assessment-of-ope)] Bibtex: ``` @article{kiyohara2023towards, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18207}, year={2023}, } ``` diff --git a/README_ja.md b/README_ja.md index 2bb935c..0c29966 100644 --- a/README_ja.md +++ b/README_ja.md @@ -9,7 +9,8 @@ [![GitHub last commit](https://img.shields.io/github/last-commit/hakuhodo-technologies/scope-rl)](https://github.com/hakuhodo-technologies/scope-rl/graphs/commit-activity) [![Documentation Status](https://readthedocs.org/projects/scope-rl/badge/?version=latest)](https://scope-rl.readthedocs.io/en/latest/) [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) -[![arXiv](https://img.shields.io/badge/arXiv-23xx.xxxxx-b31b1b.svg)](https://arxiv.org/abs/23xx.xxxxx) +[[![arXiv](https://img.shields.io/badge/arXiv-2311.18206-b31b1b.svg)](https://arxiv.org/abs/2311.18206) +[![arXiv](https://img.shields.io/badge/arXiv-2311.18207-b31b1b.svg)](https://arxiv.org/abs/2311.18207)
目次(クリックして展開) @@ -450,14 +451,14 @@ ops.visualize_conditional_value_at_risk_for_validation( Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation**
-[link]() (a preprint coming soon..) +[[arXiv](https://arxiv.org/abs/2311.18206)] [[日本語スライド](https://speakerdeck.com/aiueola/scope-rl-ja)] Bibtex: ``` @article{kiyohara2023scope, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year={2023}, } ``` @@ -466,14 +467,14 @@ Bibtex: Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation**
-[link]() (a preprint coming soon..) +[[arXiv](https://arxiv.org/abs/2311.18207)] [[日本語スライド](https://speakerdeck.com/aiueola/towards-risk-return-assessment-of-ope-ja)] Bibtex: ``` @article{kiyohara2023towards, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18207}, year={2023}, } ``` diff --git a/basicgym/README.md b/basicgym/README.md index 736ef31..32fd17a 100644 --- a/basicgym/README.md +++ b/basicgym/README.md @@ -245,14 +245,13 @@ If you use our software in your work, please cite our paper: Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation**
-[link]() (a preprint coming soon..) Bibtex: ``` @article{kiyohara2023scope, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year = {2023}, } ``` diff --git a/basicgym/README_ja.md b/basicgym/README_ja.md index 8ac35ac..f1b168e 100644 --- a/basicgym/README_ja.md +++ b/basicgym/README_ja.md @@ -246,14 +246,13 @@ class CustomizedRewardFunction(BaseRewardFunction): Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation**
-[link]() (a preprint coming soon..) Bibtex: ``` @article{kiyohara2023scope, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year = {2023}, } ``` diff --git a/docs/conf.py b/docs/conf.py index 4139df1..d370a05 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -81,7 +81,7 @@ "icon_links": [ { "name": "Speaker Deck", - "url": "https://speakerdeck.com/aiueola/ofrl-designing-an-offline-reinforcement-learning-and-policy-evaluation-platform-from-practical-perspectives", + "url": "https://speakerdeck.com/harukakiyohara_/scope-rl", "icon": "fa-brands fa-speaker-deck", "type": "fontawesome", }, diff --git a/docs/documentation/index.rst b/docs/documentation/index.rst index 8ad626b..e41356c 100644 --- a/docs/documentation/index.rst +++ b/docs/documentation/index.rst @@ -215,14 +215,13 @@ If you use our pipeline in your work, please cite our paper below. | Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito. | **SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation** - | (a preprint is coming soon..) .. code-block:: @article{kiyohara2023scope, title={SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, author={Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nakata, Kazuhide and Saito, Yuta}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year={2023} } @@ -239,7 +238,7 @@ If you use the proposed metric (SharpeRatio@k) or refer to our findings in your @article{kiyohara2023towards, title={Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation}, author={Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nakata, Kazuhide and Saito, Yuta}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18207}, year={2023} } diff --git a/docs/documentation/installation.rst b/docs/documentation/installation.rst index a5954a5..d24b760 100644 --- a/docs/documentation/installation.rst +++ b/docs/documentation/installation.rst @@ -40,7 +40,7 @@ If you use our pipeline in your work, please cite our paper below. @article{kiyohara2023scope, title={SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, author={Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nakata, Kazuhide and Saito, Yuta}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year={2023} } @@ -50,14 +50,13 @@ If you use the proposed metric (SharpeRatio@k) or refer to our findings in your | Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito. | **Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation** - | (a preprint is coming soon..) .. code-block:: @article{kiyohara2023towards, title={Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation}, author={Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nakata, Kazuhide and Saito, Yuta}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18207}, year={2023} } diff --git a/docs/documentation/news.rst b/docs/documentation/news.rst index 7630a84..a66b3b0 100644 --- a/docs/documentation/news.rst +++ b/docs/documentation/news.rst @@ -6,8 +6,8 @@ Follow us on `Google Group (scope-rl@googlegroups.com) `_ (`slides `_, `日本語スライド `_), +and (2) `Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation `_ (`slides `_, `日本語スライド `_) are now available at arXiv! **2023.7.30** Released :class:`v0.2.1` of SCOPE-RL! This release upgrades the version of d3rlpy from `1.1.1` to `2.0.4`. diff --git a/docs/documentation/sharpe_ratio.rst b/docs/documentation/sharpe_ratio.rst index 53f8b7e..324bf38 100644 --- a/docs/documentation/sharpe_ratio.rst +++ b/docs/documentation/sharpe_ratio.rst @@ -312,14 +312,13 @@ If you use the proposed metric (SharpeRatio@k) or refer to our findings in your | Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito. | **Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation** - | (a preprint is coming soon..) .. code-block:: @article{kiyohara2023towards, title={Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation}, author={Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nakata, Kazuhide and Saito, Yuta}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18207}, year={2023} } diff --git a/docs/index.rst b/docs/index.rst index 186cba6..1a6b365 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -299,14 +299,13 @@ If you use our pipeline in your work, please cite our paper below. | Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito. | **SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation** - | (a preprint is coming soon..) .. code-block:: @article{kiyohara2023scope, title={SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, author={Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nakata, Kazuhide and Saito, Yuta}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year={2023} } diff --git a/recgym/README.md b/recgym/README.md index 27fd2a2..fb97f07 100644 --- a/recgym/README.md +++ b/recgym/README.md @@ -230,14 +230,13 @@ If you use our software in your work, please cite our paper: Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation**
-[link]() (a preprint coming soon..) Bibtex: ``` @article{kiyohara2023scope, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year = {2023}, } ``` diff --git a/recgym/README_ja.md b/recgym/README_ja.md index 1db32de..4101a8d 100644 --- a/recgym/README_ja.md +++ b/recgym/README_ja.md @@ -228,14 +228,13 @@ class CustomizedUserModel(BaseUserModel): Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation**
-[link]() (a preprint coming soon..) Bibtex: ``` @article{kiyohara2023scope, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year = {2023}, } ``` diff --git a/rtbgym/README.md b/rtbgym/README.md index a0ecd8b..00ded26 100644 --- a/rtbgym/README.md +++ b/rtbgym/README.md @@ -363,14 +363,13 @@ If you use our software in your work, please cite our paper: Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation**
-[link]() (a preprint coming soon..) Bibtex: ``` @article{kiyohara2023scope, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year = {2023}, } ``` diff --git a/rtbgym/README_ja.md b/rtbgym/README_ja.md index f94b45b..ea7ddb3 100644 --- a/rtbgym/README_ja.md +++ b/rtbgym/README_ja.md @@ -359,16 +359,16 @@ custom_env = CustomizedRTBEnv( ## 引用 ソフトウェアを使用する場合は，以下の論文の引用をお願いします． + Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito.
**SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation**
-[link]() (a preprint coming soon..) Bibtex: ``` @article{kiyohara2023scope, author = {Kiyohara, Haruka and Kishimoto, Ren and Kawakami, Kosuke and Kobayashi, Ken and Nataka, Kazuhide and Saito, Yuta}, title = {SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation}, - journal={arXiv preprint arXiv:23xx.xxxxx}, + journal={arXiv preprint arXiv:2311.18206}, year = {2023}, } ```