updated DOIs + added JOSS status

README.md

@@ -3,6 +3,7 @@
 [![Build Status](https://github.com/JuliaPOMDP/CompressedBeliefMDPs.jl/actions/workflows/CI.yml/badge.svg?branch=main)](https://github.com/JuliaPOMDP/CompressedBeliefMDPs.jl/actions/workflows/CI.yml?query=branch%3Amain)
 [![Dev-Docs](https://img.shields.io/badge/docs-latest-blue.svg)](https://JuliaPOMDP.github.io/CompressedBeliefMDPs.jl/dev/)
 [![codecov](https://codecov.io/gh/JuliaPOMDP/CompressedBeliefMDPs.jl/graph/badge.svg?token=FXmEi9Fscd)](https://codecov.io/gh/JuliaPOMDP/CompressedBeliefMDPs.jl)
+[![status](https://joss.theoj.org/papers/e47a49f030233de4fbada2c389de9b34/status.svg)](https://joss.theoj.org/papers/e47a49f030233de4fbada2c389de9b34)
 
 ## Introduction
 

paper.bib

@@ -30,7 +30,7 @@ @article{Kaelbling
   pages = {99-134},
   year = {1998},
   issn = {0004-3702},
-  doi = {https://doi.org/10.1016/S0004-3702(98)00023-X},
+  doi = {10.1016/S0004-3702(98)00023-X},
   url = {https://www.sciencedirect.com/science/article/pii/S000437029800023X},
   author = {Leslie Pack Kaelbling and Michael L. Littman and Anthony R. Cassandra},
   keywords = {Planning, Uncertainty, Partially observable Markov decision processes},
@@ -43,7 +43,8 @@ @misc{carbon
       year={2023},
       eprint={2304.09352},
       archivePrefix={arXiv},
-      primaryClass={cs.AI}
+      primaryClass={cs.AI},
+      doi={10.48550/arXiv.2304.09352}
 }
 
 @article{drugs,
@@ -68,8 +69,8 @@ @article{planes
 pages = {1729881421999587},
 year = {2021},
 doi = {10.1177/1729881421999587},
-URL = { https://doi.org/10.1177/1729881421999587 },
-eprint = { https://doi.org/10.1177/1729881421999587 },
+URL = { 10.1177/1729881421999587 },
+eprint = { 10.1177/1729881421999587 },
 abstract = { Mission-critical exploration of uncertain environments requires reliable and robust mechanisms for achieving information gain. Typical measures of information gain such as Shannon entropy and KL divergence are unable to distinguish between different bimodal probability distributions or introduce bias toward one mode of a bimodal probability distribution. The use of a standard deviation (SD) metric reduces bias while retaining the ability to distinguish between higher and lower risk distributions. Areas of high SD can be safely explored through observation with an autonomous Mars Helicopter allowing safer and faster path plans for ground-based rovers. First, this study presents a single-agent information-theoretic utility-based path planning method for a highly correlated uncertain environment. Then, an information-theoretic two-stage multiagent rapidly exploring random tree framework is presented, which guides Mars helicopter through regions of high SD to reduce uncertainty for the rover. In a Monte Carlo simulation, we compare our information-theoretic framework with a rover-only approach and a naive approach, in which the helicopter scouts ahead of the rover along its planned path. Finally, the model is demonstrated in a case study on the Jezero region of Mars. Results show that the information-theoretic helicopter improves the travel time for the rover on average when compared with the rover alone or with the helicopter scouting ahead along the rover’s initially planned route. }}
 
 @INPROCEEDINGS{markets,
@@ -91,7 +92,8 @@ @article{factor
 number={5},
 pages={406},
 year={1931},
-publisher={Psychological Review Company}
+publisher={Psychological Review Company},
+doi={10.1037/h0069792}
 }
 
 
@@ -103,14 +105,16 @@ @article{autoencoder
   number={2},
   pages={233--243},
   year={1991},
-  publisher={Wiley Online Library}
+  publisher={Wiley Online Library},
+  doi={10.1002/aic.690370209}
 }
 
 @article{VAE,
   title={Auto-encoding variational bayes},
   author={Kingma, Diederik P and Welling, Max},
   journal={arXiv preprint arXiv:1312.6114},
-  year={2013}
+  year={2013},
+  doi={10.48550/arXiv.1312.6114}
 }
 
 @inproceedings{PBVI,
@@ -128,14 +132,16 @@ @article{perseus
   journal={Journal of artificial intelligence research},
   volume={24},
   pages={195--220},
-  year={2005}
+  year={2005},
+  joi={10.1613/jair.1659}
 }
 
 @article{hsvi,
   title={Point-based POMDP algorithms: Improved analysis and implementation},
   author={Smith, Trey and Simmons, Reid},
   journal={arXiv preprint arXiv:1207.1412},
-  year={2012}
+  year={2012},
+  doi={10.48550/arXiv.1207.1412}
 }
 
 @article{isomap,
@@ -146,7 +152,8 @@ @article{isomap
   number={5500},
   pages={2319--2323},
   year={2000},
-  publisher={American Association for the Advancement of Science}
+  publisher={American Association for the Advancement of Science},
+  doi={10.1126/science.290.5500.2319}
 }
 
 @article{kd-trees,
@@ -159,7 +166,7 @@ @article{kd-trees
 volume = {18},
 number = {9},
 issn = {0001-0782},
-url = {https://doi.org/10.1145/361002.361007},
+url = {10.1145/361002.361007},
 doi = {10.1145/361002.361007},
 abstract = {This paper develops the multidimensional binary search tree (or k-d tree, where k is the dimensionality of the search space) as a data structure for storage of information to be retrieved by associative searches. The k-d tree is defined and examples are given. It is shown to be quite efficient in its storage requirements. A significant advantage of this structure is that a single data structure can handle many types of queries very efficiently. Various utility algorithms are developed; their proven average running times in an n record file are: insertion, O(log n); deletion of the root, O(n(k-1)/k); deletion of a random node, O(log n); and optimization (guarantees logarithmic performance of searches), O(n log n). Search algorithms are given for partial match queries with t keys specified [proven maximum running time of O(n(k-t)/k)] and for nearest neighbor queries [empirically observed average running time of O(log n).] These performances far surpass the best currently known algorithms for these tasks. An algorithm is presented to handle any general intersection query. The main focus of this paper is theoretical. It is felt, however, that k-d trees could be quite useful in many applications, and examples of potential uses are given.},
 journal = {Commun. ACM},
@@ -184,7 +191,8 @@ @misc{Julia
       year={2012},
       eprint={1209.5145},
       archivePrefix={arXiv},
-      primaryClass={cs.PL}
+      primaryClass={cs.PL},
+      doi={10.48550/arXiv.1209.5145}
 }
 
 @INPROCEEDINGS{SARSOP,
@@ -202,7 +210,8 @@ @article{despot
   author={Somani, Adhiraj and Ye, Nan and Hsu, David and Lee, Wee Sun},
   journal={Advances in neural information processing systems},
   volume={26},
-  year={2013}
+  year={2013},
+  doi={10.1613/jair.5328},
 }
 
 @inproceedings{sunberg2018online,
@@ -211,7 +220,8 @@ @inproceedings{sunberg2018online
   booktitle={Proceedings of the International Conference on Automated Planning and Scheduling},
   volume={28},
   pages={259--263},
-  year={2018}
+  year={2018},
+  doi={10.1609/icaps.v28i1.13882}
 }
 
 @article{pomcp,
@@ -228,7 +238,8 @@ @inproceedings{mcts
   booktitle={European conference on machine learning},
   pages={282--293},
   year={2006},
-  organization={Springer}
+  organization={Springer},
+  doi={10.1007/11871842_29}
 }
 
 @inproceedings{AEMS,
@@ -248,7 +259,8 @@ @inproceedings{EPCA
  title = {A Generalization of Principal Components Analysis to the Exponential Family},
  url = {https://proceedings.neurips.cc/paper_files/paper/2001/file/f410588e48dc83f2822a880a68f78923-Paper.pdf},
  volume = {14},
- year = {2001}
+ year = {2001},
+ doi={10.7551/mitpress/1120.003.0084}
 }
 
 @misc{epca-MATLAB,
@@ -299,7 +311,8 @@ @article{kNN
  title = {Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties},
  urldate = {2024-03-19},
  volume = {57},
- year = {1989}
+ year = {1989},
+ doi={10.1037/e471672008-001}
 }
 
 @article{PCA,
@@ -309,7 +322,8 @@ @article{PCA
   year={1933},
   volume={24},
   pages={498-520},
-  url={https://api.semanticscholar.org/CorpusID:144828484}
+  url={https://api.semanticscholar.org/CorpusID:144828484},
+  doi={10.1037/h0070888}
 }
 
 @ARTICLE{kernelPCA,
@@ -347,7 +361,7 @@ @incollection{error_bound
 pages = {261-268},
 year = {1995},
 isbn = {978-1-55860-377-6},
-doi = {https://doi.org/10.1016/B978-1-55860-377-6.50040-2},
+doi = {10.1016/B978-1-55860-377-6.50040-2},
 url = {https://www.sciencedirect.com/science/article/pii/B9781558603776500402},
 author = {Geoffrey J. Gordon},
 abstract = {The success of reinforcement learning in practical problems depends on the ability to combine function approximation with temporal difference methods such as value iteration. Experiments in this area have produced mixed results; there have been both notable successes and notable disappointments. Theory has been scarce, mostly due to the difficulty of reasoning about function approximators that generalize beyond the observed data. We provide a proof of convergence for a wide class of temporal difference methods involving function approximators such as k-nearest-neighbor, and show experimentally that these methods can be useful. The proof is based on a view of function approximators as expansion or contraction mappings. In addition, we present a novel view of fitted value iteration: an approximate algorithm for one environment turns out to be an exact algorithm for a different environment.}
@@ -369,7 +383,7 @@ @article{belief-state-MDP
 pages = {174-205},
 year = {1965},
 issn = {0022-247X},
-doi = {https://doi.org/10.1016/0022-247X(65)90154-X},
+doi = {10.1016/0022-247X(65)90154-X},
 url = {https://www.sciencedirect.com/science/article/pii/0022247X6590154X},
 author = {K.J Åström}
 }