references

COeXISTENCE-PROJECT · Oct 9, 2024 · 0e949e9 · 0e949e9
1 parent 06256c3
commit 0e949e9
Show file tree

Hide file tree

Showing 7 changed files with 157 additions and 2 deletions.
diff --git a/REFERENCES.bib b/REFERENCES.bib
@@ -0,0 +1,155 @@
+@misc{bou2023torchrl,
+      title={TorchRL: A data-driven decision-making library for PyTorch}, 
+      author={Albert Bou and Matteo Bettini and Sebastian Dittert and Vikash Kumar and Shagun Sodhani and Xiaomeng Yang and Gianni De Fabritiis and Vincent Moens},
+      year={2023},
+      eprint={2306.00577},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+
+@misc{OpenStreetMap,
+   author = {{OpenStreetMap contributors}},
+   title = {{Planet dump retrieved from https://planet.osm.org }},
+   howpublished = "\url{ https://www.openstreetmap.org }",
+   year = {2017},
+ }
+
+ @article{DBLP:journals/corr/SchulmanWDRK17,
+  author       = {John Schulman and
+                  Filip Wolski and
+                  Prafulla Dhariwal and
+                  Alec Radford and
+                  Oleg Klimov},
+  title        = {Proximal Policy Optimization Algorithms},
+  journal      = {CoRR},
+  volume       = {abs/1707.06347},
+  year         = {2017},
+  url          = {http://arxiv.org/abs/1707.06347},
+  eprinttype    = {arXiv},
+  eprint       = {1707.06347},
+  timestamp    = {Mon, 13 Aug 2018 16:47:34 +0200},
+  biburl       = {https://dblp.org/rec/journals/corr/SchulmanWDRK17.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
+@article{DBLP:journals/corr/abs-2009-14471,
+  author       = {Justin K. Terry and
+                  Benjamin Black and
+                  Ananth Hari and
+                  Luis S. Santos and
+                  Clemens Dieffendahl and
+                  Niall L. Williams and
+                  Yashas Lokesh and
+                  Caroline Horsch and
+                  Praveen Ravi},
+  title        = {PettingZoo: Gym for Multi-Agent Reinforcement Learning},
+  journal      = {CoRR},
+  volume       = {abs/2009.14471},
+  year         = {2020},
+  url          = {https://arxiv.org/abs/2009.14471},
+  eprinttype    = {arXiv},
+  eprint       = {2009.14471},
+  timestamp    = {Wed, 06 Apr 2022 15:36:38 +0200},
+  biburl       = {https://dblp.org/rec/journals/corr/abs-2009-14471.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
+@book{book,
+author = {Cascetta, Ennio},
+year = {2009},
+month = {01},
+pages = {},
+title = {Transportation System Analysis: Models and Applications},
+isbn = {SBN 978-0-387-75857-2}
+}
+
+@inproceedings{SUMO2018,
+          title = {Microscopic Traffic Simulation using SUMO},
+         author = {Pablo Alvarez Lopez and Michael Behrisch and Laura Bieker-Walz and Jakob Erdmann and Yun-Pang Fl{\"o}tter{\"o}d and Robert Hilbrich and Leonhard L{\"u}cken and Johannes Rummel and Peter Wagner and Evamarie Wie{\ss}ner},
+      publisher = {IEEE},
+      booktitle = {The 21st IEEE International Conference on Intelligent Transportation Systems},
+           year = {2018},
+        journal = {IEEE Intelligent Transportation Systems Conference (ITSC)},
+       keywords = {traffic simulation, modelling, optimization},
+            url = {https://elib.dlr.de/124092/}
+ }
+
+ @book{Sutton1998,
+  added-at = {2019-07-13T10:11:53.000+0200},
+  author = {Sutton, Richard S. and Barto, Andrew G.},
+  biburl = {https://www.bibsonomy.org/bibtex/2f46601cf8b13d39d1378af0d79438b12/lanteunis},
+  edition = {Second},
+  interhash = {ac6b144aaec1819919a2fba9f705c852},
+  intrahash = {f46601cf8b13d39d1378af0d79438b12},
+  keywords = {},
+  publisher = {The MIT Press},
+  timestamp = {2019-07-13T10:11:53.000+0200},
+  title = {Reinforcement Learning: An Introduction},
+  url = {http://incompleteideas.net/book/the-book-2nd.html},
+  year = {2018 }
+}
+
+@article{DBLP:journals/corr/abs-1803-11485,
+  author       = {Tabish Rashid and
+                  Mikayel Samvelyan and
+                  Christian Schr{\"{o}}der de Witt and
+                  Gregory Farquhar and
+                  Jakob N. Foerster and
+                  Shimon Whiteson},
+  title        = {{QMIX:} Monotonic Value Function Factorisation for Deep Multi-Agent
+                  Reinforcement Learning},
+  journal      = {CoRR},
+  volume       = {abs/1803.11485},
+  year         = {2018},
+  url          = {http://arxiv.org/abs/1803.11485},
+  eprinttype    = {arXiv},
+  eprint       = {1803.11485},
+  timestamp    = {Mon, 13 Aug 2018 16:46:51 +0200},
+  biburl       = {https://dblp.org/rec/journals/corr/abs-1803-11485.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
+@article{DBLP:journals/corr/abs-2011-09533,
+  author       = {Christian Schr{\"{o}}der de Witt and
+                  Tarun Gupta and
+                  Denys Makoviichuk and
+                  Viktor Makoviychuk and
+                  Philip H. S. Torr and
+                  Mingfei Sun and
+                  Shimon Whiteson},
+  title        = {Is Independent Learning All You Need in the StarCraft Multi-Agent
+                  Challenge?},
+  journal      = {CoRR},
+  volume       = {abs/2011.09533},
+  year         = {2020},
+  url          = {https://arxiv.org/abs/2011.09533},
+  eprinttype    = {arXiv},
+  eprint       = {2011.09533},
+  timestamp    = {Wed, 25 Nov 2020 16:34:14 +0100},
+  biburl       = {https://dblp.org/rec/journals/corr/abs-2011-09533.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
+@article{DBLP:journals/corr/SunehagLGCZJLSL17,
+  author       = {Peter Sunehag and
+                  Guy Lever and
+                  Audrunas Gruslys and
+                  Wojciech Marian Czarnecki and
+                  Vin{\'{\i}}cius Flores Zambaldi and
+                  Max Jaderberg and
+                  Marc Lanctot and
+                  Nicolas Sonnerat and
+                  Joel Z. Leibo and
+                  Karl Tuyls and
+                  Thore Graepel},
+  title        = {Value-Decomposition Networks For Cooperative Multi-Agent Learning},
+  journal      = {CoRR},
+  volume       = {abs/1706.05296},
+  year         = {2017},
+  url          = {http://arxiv.org/abs/1706.05296},
+  eprinttype    = {arXiv},
+  eprint       = {1706.05296},
+  timestamp    = {Mon, 13 Aug 2018 16:46:26 +0200},
+  biburl       = {https://dblp.org/rec/journals/corr/SunehagLGCZJLSL17.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
diff --git a/docs/img/csomor2.png b/docs/img/csomor2.png
diff --git a/tutorials/img/env.png → docs/img/env.png b/tutorials/img/env.png → docs/img/env.png
diff --git a/docs/img/paths.png b/docs/img/paths.png
diff --git a/tutorials/img/qmix.png → docs/img/qmix.png b/tutorials/img/qmix.png → docs/img/qmix.png
diff --git a/tutorials/MarlAlgorithms/mappo_ippo_mutation.ipynb b/tutorials/MarlAlgorithms/mappo_ippo_mutation.ipynb
@@ -35,7 +35,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "![Alt text](../img/env.png)\n"
+    "![Alt text](../../docs/img/env.png)\n"
    ]
   },
   {

diff --git a/tutorials/MarlAlgorithms/qmix_mutation.ipynb b/tutorials/MarlAlgorithms/qmix_mutation.ipynb
@@ -21,7 +21,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "![Qmix](../img/qmix.png)\n",
+    "![Qmix](../../docs/img/qmix.png)\n",
     "\n",
     "\n",
     "> Picture taken from QMIX [paper](https://arxiv.org/pdf/1803.11485).\n"