benchmarks.bib

@MISC{noauthor_undated-mj,
  title       = "robogym: Robotics Gym Environments",
  institution = "Github"
}

@ARTICLE{Tanner2009-ps,
  title    = "{RL-Glue}: {Language-Independent} Software for
              {Reinforcement-Learning} Experiments",
  author   = "Tanner, Brian and White, Adam",
  journal  = "Journal of machine learning research: JMLR",
  volume   =  10,
  number   =  74,
  pages    = "2133--2136",
  year     =  2009
}

@INPROCEEDINGS{Laird2010-aw,
  title           = "Cognitive Architecture Requirements for Achieving {AGI}",
  booktitle       = "Proceedings of the 3d Conference on Artificial General
                     Intelligence ({AGI-10})",
  author          = "Laird, John E and Wray, III, Robert E",
  publisher       = "Atlantis Press",
  year            =  2010,
  address         = "Paris, France",
  conference      = "3d Conference on Artificial General Intelligence (AGI-10)",
  location        = "Lugano, Switzerland"
}

@INPROCEEDINGS{Whiteson2010-rk,
  title     = "The reinforcement learning competitions",
  booktitle = "{AI} Magazine",
  author    = "Whiteson, Shimon and Tanner, Brian and White, Adam",
  year      =  2010
}

@INPROCEEDINGS{Whiteson2011-uj,
  title           = "Protecting against evaluation overfitting in empirical
                     reinforcement learning",
  booktitle       = "2011 {IEEE} Symposium on Adaptive Dynamic Programming and
                     Reinforcement Learning ({ADPRL})",
  author          = "Whiteson, Shimon and Tanner, Brian and Taylor, Matthew E
                     and Stone, Peter",
  publisher       = "IEEE",
  month           =  apr,
  year            =  2011,
  conference      = "2011 Ieee Symposium On Adaptive Dynamic Programming And
                     Reinforcement Learning",
  location        = "Paris, France"
}

@ARTICLE{Schaul2011-io,
  title         = "Measuring Intelligence through Games",
  author        = "Schaul, Tom and Togelius, Julian and Schmidhuber, J{\"u}rgen",
  month         =  sep,
  year          =  2011,
  archivePrefix = "arXiv",
  primaryClass  = "cs.AI",
  eprint        = "1109.1314"
}

@ARTICLE{Adams2012-vy,
  title     = "Mapping the landscape of human-level artificial general
               intelligence",
  author    = "Adams, Sam and Arel, Itmar and Bach, Joscha and Coop, Robert and
               Furlan, Rod and Goertzel, Ben and Hall, J Storrs and
               Samsonovich, Alexei and Scheutz, Matthias and Schlesinger,
               Matthew and Shapiro, Stuart C and Sowa, John",
  journal   = "AI magazine",
  publisher = "Association for the Advancement of Artificial Intelligence
               (AAAI)",
  volume    =  33,
  number    =  1,
  pages     = "25--42",
  month     =  mar,
  year      =  2012
}

@ARTICLE{Bellemare2012-si,
  title         = "The Arcade Learning Environment: An Evaluation Platform for
                   General Agents",
  author        = "Bellemare, Marc G and Naddaf, Yavar and Veness, Joel and
                   Bowling, Michael",
  month         =  jul,
  year          =  2012,
  archivePrefix = "arXiv",
  primaryClass  = "cs.AI",
  eprint        = "1207.4708"
}

@INPROCEEDINGS{Schaul2013-kg,
  title           = "A video game description language for model-based or
                     interactive learning",
  booktitle       = "2013 {IEEE} Conference on Computational Inteligence in
                     Games ({CIG})",
  author          = "Schaul, Tom",
  publisher       = "IEEE",
  month           =  aug,
  year            =  2013,
  conference      = "2013 IEEE Conference on Computational Intelligence and
                     Games (CIG)",
  location        = "Niagara Falls, ON, Canada"
}

@MISC{Riedmiller2013-gs,
  title    = "{CLSquare}: Closed Loop Simulation System",
  author   = "Riedmiller, Martin and Blum, Manuel and Lampe, Thomas and Hafner,
              Roland and Lange, Sascha and Timmer, Stephan",
  month    =  aug,
  year     =  2013
}

@INPROCEEDINGS{Coleman2014-lm,
  title     = "Automated generation of environments to test the general
               learning capabilities of {AI} agents",
  booktitle = "Proceedings of the 2014 Annual Conference on Genetic and
               Evolutionary Computation",
  author    = "Coleman, Oliver J and Blair, Alan D and Clune, Jeff",
  publisher = "Association for Computing Machinery",
  pages     = "161--168",
  series    = "GECCO '14",
  month     =  jul,
  year      =  2014,
  address   = "New York, NY, USA",
  location  = "Vancouver, BC, Canada"
}

@ARTICLE{Duan2016-kl,
  title         = "Benchmarking Deep Reinforcement Learning for Continuous
                   Control",
  author        = "Duan, Yan and Chen, Xi and Houthooft, Rein and Schulman,
                   John and Abbeel, Pieter",
  month         =  apr,
  year          =  2016,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1604.06778"
}

@ARTICLE{Kempka2016-my,
  title         = "{ViZDoom}: A Doom-based {AI} Research Platform for Visual
                   Reinforcement Learning",
  author        = "Kempka, Micha{\l} and Wydmuch, Marek and Runc, Grzegorz and
                   Toczek, Jakub and Ja{\'s}kowski, Wojciech",
  month         =  may,
  year          =  2016,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1605.02097"
}

@ARTICLE{Brockman2016-jw,
  title         = "{OpenAI} Gym",
  author        = "Brockman, Greg and Cheung, Vicki and Pettersson, Ludwig and
                   Schneider, Jonas and Schulman, John and Tang, Jie and
                   Zaremba, Wojciech",
  month         =  jun,
  year          =  2016,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1606.01540"
}

@INPROCEEDINGS{Johnson2016-rt,
  title     = "The Malmo platform for artificial intelligence experimentation",
  booktitle = "Proceedings of the {Twenty-Fifth} International Joint Conference
               on Artificial Intelligence",
  author    = "Johnson, Matthew and Hofmann, Katja and Hutton, Tim and Bignell,
               David",
  publisher = "AAAI Press",
  pages     = "4246--4247",
  series    = "IJCAI'16",
  month     =  jul,
  year      =  2016,
  location  = "New York, New York, USA"
}

@ARTICLE{Perez-Liebana2016-me,
  title   = "The 2014 General Video Game Playing Competition",
  author  = "Perez-Liebana, Diego and Samothrakis, Spyridon and Togelius,
             Julian and Schaul, Tom and Lucas, Simon M and Cou{\"e}toux, Adrien
             and Lee, Jerry and Lim, Chong-U and Thompson, Tommy",
  journal = "IEEE Transactions on Computational Intelligence in AI and Games",
  volume  =  8,
  number  =  3,
  pages   = "229--243",
  month   =  sep,
  year    =  2016
}

@ARTICLE{Beattie2016-gt,
  title         = "{DeepMind} Lab",
  author        = "Beattie, Charles and Leibo, Joel Z and Teplyashin, Denis and
                   Ward, Tom and Wainwright, Marcus and K{\"u}ttler, Heinrich
                   and Lefrancq, Andrew and Green, Simon and Vald{\'e}s,
                   V{\'\i}ctor and Sadik, Amir and Schrittwieser, Julian and
                   Anderson, Keith and York, Sarah and Cant, Max and Cain, Adam
                   and Bolton, Adrian and Gaffney, Stephen and King, Helen and
                   Hassabis, Demis and Legg, Shane and Petersen, Stig",
  month         =  dec,
  year          =  2016,
  archivePrefix = "arXiv",
  primaryClass  = "cs.AI",
  eprint        = "1612.03801"
}

@BOOK{Hernandez-Orallo2017-mm,
  title     = "The measure of all minds: Evaluating natural and artificial
               intelligence",
  author    = "Hernandez-Orallo, Jose",
  publisher = "Cambridge University Press",
  month     =  jan,
  year      =  2017,
  address   = "Cambridge, England"
}

@ARTICLE{Rajeswaran2017-mr,
  title         = "Learning Complex Dexterous Manipulation with Deep
                   Reinforcement Learning and Demonstrations",
  author        = "Rajeswaran, Aravind and Kumar, Vikash and Gupta, Abhishek
                   and Vezzani, Giulia and Schulman, John and Todorov, Emanuel
                   and Levine, Sergey",
  month         =  sep,
  year          =  2017,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1709.10087"
}

@ARTICLE{Machado2018-ck,
  title     = "Revisiting the arcade learning environment: evaluation protocols
               and open problems for general agents",
  author    = "Machado, Marlos C and Bellemare, Marc G and Talvitie, Erik and
               Veness, Joel and Hausknecht, Matthew and Bowling, Michael",
  journal   = "The journal of artificial intelligence research",
  publisher = "AI Access Foundation",
  volume    =  61,
  number    =  1,
  pages     = "523--562",
  month     =  jan,
  year      =  2018,
  address   = "El Segundo, CA, USA"
}

@INPROCEEDINGS{Fan2018-xa,
  title    = "{SURREAL}: Open-source reinforcement learning framework and robot
              manipulation benchmark",
  author   = "Fan, Linxi and Zhu, Yuke",
  year     =  2018
}

@ARTICLE{Leibo2018-zh,
  title         = "Psychlab: A Psychology Laboratory for Deep Reinforcement
                   Learning Agents",
  author        = "Leibo, Joel Z and de Masson d'Autume, Cyprien and Zoran,
                   Daniel and Amos, David and Beattie, Charles and Anderson,
                   Keith and Casta{\~n}eda, Antonio Garc{\'\i}a and Sanchez,
                   Manuel and Green, Simon and Gruslys, Audrunas and Legg,
                   Shane and Hassabis, Demis and Botvinick, Matthew M",
  month         =  jan,
  year          =  2018,
  archivePrefix = "arXiv",
  primaryClass  = "cs.AI",
  eprint        = "1801.08116"
}

@ARTICLE{Nichol2018-ho,
  title         = "Gotta Learn Fast: A New Benchmark for Generalization in {RL}",
  author        = "Nichol, Alex and Pfau, Vicki and Hesse, Christopher and
                   Klimov, Oleg and Schulman, John",
  month         =  apr,
  year          =  2018,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1804.03720"
}

@ARTICLE{Juliani2018-dl,
  title         = "Unity: A General Platform for Intelligent Agents",
  author        = "Juliani, Arthur and Berges, Vincent-Pierre and Teng, Ervin
                   and Cohen, Andrew and Harper, Jonathan and Elion, Chris and
                   Goy, Chris and Gao, Yuan and Henry, Hunter and Mattar,
                   Marwan and Lange, Danny",
  month         =  sep,
  year          =  2018,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1809.02627"
}

@ARTICLE{Zhang2018-wp,
  title         = "Natural Environment Benchmarks for Reinforcement Learning",
  author        = "Zhang, Amy and Wu, Yuxin and Pineau, Joelle",
  month         =  nov,
  year          =  2018,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1811.06032"
}

@ARTICLE{Cobbe2018-qa,
  title         = "Quantifying Generalization in Reinforcement Learning",
  author        = "Cobbe, Karl and Klimov, Oleg and Hesse, Chris and Kim,
                   Taehoon and Schulman, John",
  month         =  dec,
  year          =  2018,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1812.02341"
}

@INPROCEEDINGS{Fortunato2019-ne,
  title     = "Generalization of Reinforcement Learners with Working and
               Episodic Memory",
  booktitle = "Advances in Neural Information Processing Systems",
  author    = "Fortunato, Meire and Tan, Melissa and Faulkner, Ryan and Hansen,
               Steven and Badia, Adri{\`a} Puigdom{\`e}nech and Buttimore,
               Gavin and Deck, Charles and Leibo, Joel Z and Blundell, Charles",
  pages     = "12448--12457",
  year      =  2019
}

@UNPUBLISHED{Ray2019-uk,
  title    = "Benchmarking safe exploration in deep reinforcement learning",
  author   = "Ray, Alex and Achiam, Joshua and Amodei, Dario",
  year     =  2019
}

@INPROCEEDINGS{Cote2019-fw,
  title     = "{TextWorld}: A Learning Environment for {Text-Based} Games",
  booktitle = "Computer Games",
  author    = "C{\^o}t{\'e}, Marc-Alexandre and K{\'a}d{\'a}r, {\'A}kos and
               Yuan, Xingdi and Kybartas, Ben and Barnes, Tavian and Fine,
               Emery and Moore, James and Hausknecht, Matthew and El Asri,
               Layla and Adada, Mahmoud and Tay, Wendy and Trischler, Adam",
  publisher = "Springer International Publishing",
  pages     = "41--75",
  year      =  2019
}

@ARTICLE{Juliani2019-aa,
  title         = "Obstacle Tower: A Generalization Challenge in Vision,
                   Control, and Planning",
  author        = "Juliani, Arthur and Khalifa, Ahmed and Berges,
                   Vincent-Pierre and Harper, Jonathan and Teng, Ervin and
                   Henry, Hunter and Crespi, Adam and Togelius, Julian and
                   Lange, Danny",
  month         =  feb,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.AI",
  eprint        = "1902.01378"
}

@ARTICLE{Savva2019-mo,
  title         = "Habitat: A Platform for Embodied {AI} Research",
  author        = "Savva, Manolis and Kadian, Abhishek and Maksymets, Oleksandr
                   and Zhao, Yili and Wijmans, Erik and Jain, Bhavana and
                   Straub, Julian and Liu, Jia and Koltun, Vladlen and Malik,
                   Jitendra and Parikh, Devi and Batra, Dhruv",
  month         =  apr,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.CV",
  eprint        = "1904.01201"
}

@ARTICLE{Guss2019-qd,
  title         = "The {MineRL} 2019 Competition on Sample Efficient
                   Reinforcement Learning using Human Priors",
  author        = "Guss, William H and Codel, Cayden and Hofmann, Katja and
                   Houghton, Brandon and Kuno, Noboru and Milani, Stephanie and
                   Mohanty, Sharada and Liebana, Diego Perez and Salakhutdinov,
                   Ruslan and Topin, Nicholay and Veloso, Manuela and Wang,
                   Phillip",
  month         =  apr,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1904.10079"
}

@ARTICLE{Wang2019-sg,
  title         = "Benchmarking {Model-Based} Reinforcement Learning",
  author        = "Wang, Tingwu and Bao, Xuchan and Clavera, Ignasi and Hoang,
                   Jerrick and Wen, Yeming and Langlois, Eric and Zhang,
                   Shunshi and Zhang, Guodong and Abbeel, Pieter and Ba, Jimmy",
  month         =  jul,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1907.02057"
}

@ARTICLE{Agarwal2019-gr,
  title         = "An Optimistic Perspective on Offline Reinforcement Learning",
  author        = "Agarwal, Rishabh and Schuurmans, Dale and Norouzi, Mohammad",
  month         =  jul,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1907.04543"
}

@ARTICLE{Kurach2019-lh,
  title         = "Google Research Football: A Novel Reinforcement Learning
                   Environment",
  author        = "Kurach, Karol and Raichuk, Anton and Sta{\'n}czyk, Piotr and
                   Zaj{\k a}c, Micha{\l} and Bachem, Olivier and Espeholt,
                   Lasse and Riquelme, Carlos and Vincent, Damien and
                   Michalski, Marcin and Bousquet, Olivier and Gelly, Sylvain",
  month         =  jul,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1907.11180"
}

@ARTICLE{Guss2019-vb,
  title         = "{MineRL}: A {Large-Scale} Dataset of Minecraft
                   Demonstrations",
  author        = "Guss, William H and Houghton, Brandon and Topin, Nicholay
                   and Wang, Phillip and Codel, Cayden and Veloso, Manuela and
                   Salakhutdinov, Ruslan",
  month         =  jul,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1907.13440"
}

@ARTICLE{Osband2019-vz,
  title         = "Behaviour Suite for Reinforcement Learning",
  author        = "Osband, Ian and Doron, Yotam and Hessel, Matteo and
                   Aslanides, John and Sezener, Eren and Saraiva, Andre and
                   McKinney, Katrina and Lattimore, Tor and Szepesvari, Csaba
                   and Singh, Satinder and Van Roy, Benjamin and Sutton,
                   Richard and Silver, David and Van Hasselt, Hado",
  month         =  aug,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1908.03568"
}

@ARTICLE{Le_Paine2019-nh,
  title         = "Making Efficient Use of Demonstrations to Solve Hard
                   Exploration Problems",
  author        = "Le Paine, Tom and Gulcehre, Caglar and Shahriari, Bobak and
                   Denil, Misha and Hoffman, Matt and Soyer, Hubert and
                   Tanburn, Richard and Kapturowski, Steven and Rabinowitz,
                   Neil and Williams, Duncan and Barth-Maron, Gabriel and Wang,
                   Ziyu and de Freitas, Nando and {Worlds Team}",
  month         =  sep,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1909.01387"
}

@ARTICLE{Ahn2019-ll,
  title         = "{ROBEL}: Robotics Benchmarks for Learning with {Low-Cost}
                   Robots",
  author        = "Ahn, Michael and Zhu, Henry and Hartikainen, Kristian and
                   Ponte, Hugo and Gupta, Abhishek and Levine, Sergey and
                   Kumar, Vikash",
  month         =  sep,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.RO",
  eprint        = "1909.11639"
}

@ARTICLE{James2019-gv,
  title         = "{RLBench}: The Robot Learning Benchmark \& Learning
                   Environment",
  author        = "James, Stephen and Ma, Zicong and Arrojo, David Rovick and
                   Davison, Andrew J",
  month         =  sep,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.RO",
  eprint        = "1909.12271"
}

@ARTICLE{Fujimoto2019-iw,
  title         = "Benchmarking Batch Deep Reinforcement Learning Algorithms",
  author        = "Fujimoto, Scott and Conti, Edoardo and Ghavamzadeh, Mohammad
                   and Pineau, Joelle",
  month         =  oct,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1910.01708"
}

@ARTICLE{Yu2019-jm,
  title         = "{Meta-World}: A Benchmark and Evaluation for {Multi-Task}
                   and Meta Reinforcement Learning",
  author        = "Yu, Tianhe and Quillen, Deirdre and He, Zhanpeng and Julian,
                   Ryan and Narayan, Avnish and Shively, Hayden and Bellathur,
                   Adithya and Hausman, Karol and Finn, Chelsea and Levine,
                   Sergey",
  month         =  oct,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1910.10897"
}

@ARTICLE{Collins2019-wp,
  title         = "Benchmarking Simulated Robotic Manipulation through a Real
                   World Dataset",
  author        = "Collins, Jack and McVicar, Jessie and Wedlock, David and
                   Brown, Ross and Howard, David and Leitner, J{\"u}rgen",
  month         =  nov,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.RO",
  eprint        = "1911.01557"
}

@ARTICLE{Chollet2019-qa,
  title         = "On the Measure of Intelligence",
  author        = "Chollet, Fran{\c c}ois",
  month         =  nov,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.AI",
  eprint        = "1911.01547"
}

@ARTICLE{Lee2019-fs,
  title         = "{IKEA} Furniture Assembly Environment for {Long-Horizon}
                   Complex Manipulation Tasks",
  author        = "Lee, Youngwoon and Hu, Edward S and Yang, Zhengyu and Yin,
                   Alex and Lim, Joseph J",
  month         =  nov,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.RO",
  eprint        = "1911.07246"
}

@ARTICLE{Cobbe2019-wc,
  title         = "Leveraging Procedural Generation to Benchmark Reinforcement
                   Learning",
  author        = "Cobbe, Karl and Hesse, Christopher and Hilton, Jacob and
                   Schulman, John",
  month         =  dec,
  year          =  2019,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "1912.01588"
}

@ARTICLE{Platanios2020-os,
  title    = "Jelly Bean World: A Testbed for {Never-Ending} Learning",
  author   = "Platanios, Emmanouil Antonios and Saparov, Abulhair and Mitchell,
              Tom",
  journal  = "undefined",
  year     =  2020
}

@INPROCEEDINGS{Crosby2020-ei,
  title     = "The {Animal-AI} Testbed and Competition",
  booktitle = "Proceedings of the {NeurIPS} 2019 Competition and Demonstration
               Track",
  author    = "Crosby, Matthew and Beyret, Benjamin and Shanahan, Murray and
               Hern{\'a}ndez-Orallo, Jos{\'e} and Cheke, Lucy and Halina, Marta",
  editor    = "Escalante, Hugo Jair and Hadsell, Raia",
  publisher = "PMLR",
  volume    =  123,
  pages     = "164--176",
  series    = "Proceedings of Machine Learning Research",
  year      =  2020
}

@ARTICLE{Dulac-Arnold2020-im,
  title         = "An empirical investigation of the challenges of real-world
                   reinforcement learning",
  author        = "Dulac-Arnold, Gabriel and Levine, Nir and Mankowitz, Daniel
                   J and Li, Jerry and Paduraru, Cosmin and Gowal, Sven and
                   Hester, Todd",
  month         =  mar,
  year          =  2020,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "2003.11881"
}

@ARTICLE{Fu2020-nn,
  title         = "{D4RL}: Datasets for Deep {Data-Driven} Reinforcement
                   Learning",
  author        = "Fu, Justin and Kumar, Aviral and Nachum, Ofir and Tucker,
                   George and Levine, Sergey",
  month         =  apr,
  year          =  2020,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "2004.07219"
}

@ARTICLE{Tassa2020-dp,
  title         = "dm\_control: Software and Tasks for Continuous Control",
  author        = "Tassa, Yuval and Tunyasuvunakool, Saran and Muldal, Alistair
                   and Doron, Yotam and Trochim, Piotr and Liu, Siqi and Bohez,
                   Steven and Merel, Josh and Erez, Tom and Lillicrap, Timothy
                   and Heess, Nicolas",
  month         =  jun,
  year          =  2020,
  archivePrefix = "arXiv",
  primaryClass  = "cs.RO",
  eprint        = "2006.12983"
}

@ARTICLE{Gulcehre2020-om,
  title         = "{RL} Unplugged: A suite of benchmarks for offline
                   reinforcement learning",
  author        = "Gulcehre, Caglar and Wang, Ziyu and Novikov, Alexander and
                   Paine, Tom Le and Colmenarejo, Sergio Gomez and Zolna,
                   Konrad and Agarwal, Rishabh and Merel, Josh and Mankowitz,
                   Daniel and Paduraru, Cosmin and Dulac-Arnold, Gabriel and
                   Li, Jerry and Norouzi, Mohammad and Hoffman, Matt and
                   Nachum, Ofir and Tucker, George and Heess, Nicolas and de
                   Freitas, Nando",
  month         =  jun,
  year          =  2020,
  copyright     = "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "2006.13888"
}

@ARTICLE{Kuttler2020-fv,
  title         = "The {NetHack} Learning Environment",
  author        = "K{\"u}ttler, Heinrich and Nardelli, Nantas and Miller,
                   Alexander H and Raileanu, Roberta and Selvatici, Marco and
                   Grefenstette, Edward and Rockt{\"a}schel, Tim",
  month         =  jun,
  year          =  2020,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "2006.13760"
}

@INPROCEEDINGS{Mbuwir2020-zt,
  title     = "Benchmarking reinforcement learning algorithms for demand
               response applications",
  booktitle = "2020 {IEEE} {PES} Innovative Smart Grid Technologies Europe
               ({ISGT-Europe})",
  author    = "Mbuwir, Brida V and Manna, Carlo and Spiessens, Fred and
               Deconinck, Geert",
  pages     = "289--293",
  month     =  oct,
  year      =  2020
}

@MISC{Kannan2021-sz,
  title        = "{RoboDesk} environment v0",
  author       = "Kannan, Harini and Hafner, Danijar and Finn, Chelsea and
                  Erhan, Dumitru",
  year         =  2021,
  howpublished = "\url{https://github.com/google-research/robodesk}"
}

@ARTICLE{Wang2021-fb,
  title         = "Alchemy: A structured task distribution for
                   meta-reinforcement learning",
  author        = "Wang, Jane X and King, Michael and Porcel, Nicolas and
                   Kurth-Nelson, Zeb and Zhu, Tina and Deck, Charlie and Choy,
                   Peter and Cassin, Mary and Reynolds, Malcolm and Song,
                   Francis and Buttimore, Gavin and Reichert, David P and
                   Rabinowitz, Neil and Matthey, Loic and Hassabis, Demis and
                   Lerchner, Alexander and Botvinick, Matthew",
  month         =  feb,
  year          =  2021,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "2102.02926"
}

@UNPUBLISHED{Samvelyan2021-ks,
  title    = "{MiniHack} the Planet: A Sandbox for {Open-Ended} Reinforcement
              Learning Research",
  author   = "Samvelyan, Mikayel and Kirk, Robert and Kurin, Vitaly and
              Parker-Holder, Jack and Jiang, Minqi and Hambro, Eric and
              Petroni, Fabio and Kuttler, Heinrich and Grefenstette, Edward and
              Rockt{\"a}schel, Tim",
  month    =  jun,
  year     =  2021
}

@ARTICLE{Daniel_Freeman2021-cf,
  title         = "Brax -- A Differentiable Physics Engine for Large Scale
                   Rigid Body Simulation",
  author        = "Daniel Freeman, C and Frey, Erik and Raichuk, Anton and
                   Girgin, Sertan and Mordatch, Igor and Bachem, Olivier",
  month         =  jun,
  year          =  2021,
  archivePrefix = "arXiv",
  primaryClass  = "cs.RO",
  eprint        = "2106.13281"
}

@ARTICLE{Szot2021-cs,
  title         = "Habitat 2.0: Training Home Assistants to Rearrange their
                   Habitat",
  author        = "Szot, Andrew and Clegg, Alex and Undersander, Eric and
                   Wijmans, Erik and Zhao, Yili and Turner, John and Maestre,
                   Noah and Mukadam, Mustafa and Chaplot, Devendra and
                   Maksymets, Oleksandr and Gokaslan, Aaron and Vondrus,
                   Vladimir and Dharur, Sameer and Meier, Franziska and Galuba,
                   Wojciech and Chang, Angel and Kira, Zsolt and Koltun,
                   Vladlen and Malik, Jitendra and Savva, Manolis and Batra,
                   Dhruv",
  month         =  jun,
  year          =  2021,
  archivePrefix = "arXiv",
  primaryClass  = "cs.LG",
  eprint        = "2106.14405"
}