Update report (#453)

* Update report

* fix cspell

* Make some changes

* Update with implementation details

* Update bibliography.bib

* Fix some mistakes

* Fix typo

* Make the suggested changes

* Update date

* Fix code

* add installation instructions

* Update cspell.json

* Update cspell.json

* Added the mentioned changes

Author: Mobius1D

.cspell/cspell.json

@@ -122,6 +122,8 @@
         "turbulences",
         "Decompressor",
         "MADDPG",
+        "Prasidh",
+        "Srikumar",
         "Caglar",
         "Gulcehre",
         "Novikov",
@@ -142,6 +144,7 @@
         "reparamaterize",
         "MADDPG",
         "rldatasets",
+        "Trichy",
         "Prasidh",
         "Srikumar"
     ],

docs/homepage/blog/index.md

@@ -3,7 +3,7 @@
 @def is_enable_toc = false
 
 - [An Introduction to ReinforcementLearning.jl: Design, Implementations and Thoughts](/blog/an_introduction_to_reinforcement_learning_jl_design_implementations_thoughts)
-
+- [Establish a General Pipeline for Offline Reinforcement Learning Evaluation (Summer OSPP Project 210370741) Mid-term Report](/blog/ospp_mid-term_report_210370741)
 - Notebooks for the book: [*Reinforcement Learning: an Introduction 2nd
   Edition*](https://github.com/JuliaReinforcementLearning/ReinforcementLearningAnIntroduction.jl)
 

docs/homepage/blog/ospp_mid-term_report_210370741/bibliography.bib

@@ -0,0 +1,34 @@
+@misc{fu2020d4rl,
+    title={D4RL: Datasets for Deep Data-Driven Reinforcement Learning},
+    author={Justin Fu and Aviral Kumar and Ofir Nachum and George Tucker and Sergey Levine},
+    year={2020},
+    eprint={2004.07219},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+@inproceedings{agarwal2020optimistic,
+  title={An Optimistic Perspective on Offline Reinforcement Learning},
+  author={Agarwal, Rishabh and Schuurmans, Dale and Norouzi, Mohammad},
+  journal={International Conference on Machine Learning},
+  year={2020}
+}
+@misc{gulcehre2020rl,
+    title={RL Unplugged: Benchmarks for Offline Reinforcement Learning},
+    author={Caglar Gulcehre and Ziyu Wang and Alexander Novikov and Tom Le Paine
+        and  Sergio Gómez Colmenarejo and Konrad Zolna and Rishabh Agarwal and
+        Josh Merel and Daniel Mankowitz and Cosmin Paduraru and Gabriel
+        Dulac-Arnold and Jerry Li and Mohammad Norouzi and Matt Hoffman and
+        Ofir Nachum and George Tucker and Nicolas Heess and Nando deFreitas},
+    year={2020},
+    eprint={2006.13888},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+@misc{fu2021benchmarks,
+      title={Benchmarks for Deep Off-Policy Evaluation}, 
+      author={Justin Fu and Mohammad Norouzi and Ofir Nachum and George Tucker and Ziyu Wang and Alexander Novikov and Mengjiao Yang and Michael R. Zhang and Yutian Chen and Aviral Kumar and Cosmin Paduraru and Sergey Levine and Tom Le Paine},
+      year={2021},
+      eprint={2103.16596},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}