Reinforcement Learning Journal (RLJ)

<!DOCTYPE dblpsubmission SYSTEM "https://dblp.org/xml/subm/dblpsubmission.dtd">Philip S. Thomas, Feryal Behbahani, Glen Berseth, Scott M. Jordan, Scott Niekum, Andrew Patterson, Eugene Vinitsky, Adam White, Martha White, Amy ZhangReinforcement Learning Journal (RLJ)RLJ2024979-8-218-41163-3https://rlj.cs.umass.edu/2996-85692996-8577Max Olan Smith;Michael P. WellmanCo-Learning Empirical Games & World Models1-151Woojin Jeong;Seungki MinImproving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits16-281Shuang Wu;Arash A. AminiGraph Neural Thompson Sampling29-631Junxiong Wang;Kaiwen Wang;Yueying Li;Nathan Kallus;Immanuel Trummer;Wen SunJoinGym: An Efficient Join Order Selection Environment64-911Antonin Raffin;Olivier Sigaud;Jens Kober;Alin Albu-Schaeffer;João Silvério;Freek StulpAn Open-Loop Baseline for Reinforcement Learning Locomotion Tasks92-1071Raphaël Avalos;Eugenio Bargiacchi;Ann Nowe;Diederik Roijers;Frans A OliehoekOnline Planning in POMDPs with State-Requests108-1291Abdulaziz Almuzairee;Nicklas Hansen;Henrik I ChristensenA Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning130-1571Robert J. Moss;Anthony Corso;Jef Caers;Mykel KochenderferBetaZero: Belief-State Planning for Long-Horizon POMDPs using Learned Approximations158-1811Audrey Huang;Mohammad Ghavamzadeh;Nan Jiang;Marek PetrikNon-adaptive Online Finetuning for Offline Reinforcement Learning182-1971Nicholas E. Corrado;Yuxiao Qu;John U. Balis;Adam Labiosa;Josiah P. HannaGuided Data Augmentation for Offline Reinforcement Learning and Imitation Learning198-2151Michael Lu;Matin Aghaei;Anant Raj;Sharan VaswaniTowards Principled, Practical Policy Gradient for Bandits and Tabular MDPs216-2821Benjamin Freed;Thomas Wei;Roberto Calandra;Jeff Schneider;Howie ChosetUnifying Model-Based and Model-Free Reinforcement Learning with Equivalent Policy Sets283-3011Noah Golowich;Ankur MoitraThe Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation302-3411Max Rudolph;Caleb Chuck;Kevin Black;Misha Lvovsky;Scott Niekum;Amy ZhangLearning Action-based Representations Using Invariance342-3651Oliver Järnefelt;Mahdi Kallel;Carlo D'EramoCyclicity-Regularized Coordination Graphs366-3791Aditya Kapoor;Benjamin Freed;Jeff Schneider;Howie ChosetAssigning Credit with Partial Reward Decoupling in Multi-Agent Proximal Policy Optimization380-3991Quentin Delfosse;Jannis Blüml;Bjarne Gregori;Sebastian Sztwiertnia;Kristian KerstingOCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments400-4491Jacob Beck;Matthew Thomas Jackson;Risto Vuorio;Zheng Xiong;Shimon WhitesonSplAgger: Split Aggregation for Meta-Reinforcement Learning450-4691Nan Jiang;Jinzhao Li;Yexiang XueA Tighter Convergence Proof of Reverse Experience Replay470-4801Qingfeng Lan;A. Rupam Mahmood;Shuicheng YAN;Zhongwen XuLearning to Optimize for Reinforcement Learning481-4972Mhairi Dunion;Stefano V AlbrechtMulti-view Disentanglement for Reinforcement Learning with Multiple Cameras498-5152Trevor McInroe;Adam Jelley;Stefano V Albrecht;Amos StorkeyPlanning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning516-5462Adriana Hugessen;Roger Creus Castanyer;Faisal Mohamed;Glen BersethSurprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning547-5622Alex Ayoub;David Szepesvari;Francesco Zanini;Bryan Chan;Dhawal Gupta;Bruno Castro da Silva;Dale SchuurmansMitigating the Curse of Horizon in Monte-Carlo Returns563-5722Yudong Luo;Yangchen Pan;Han Wang;Philip Torr;Pascal PoupartA Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization573-5922Gersi Doko;Guang Yang;Daniel S. Brown;Marek PetrikROIL: Robust Offline Imitation Learning without Trajectories593-6052Edan Jacob Meyer;Adam White;Marlos C. MachadoHarnessing Discrete Representations for Continual Reinforcement Learning606-6282David Abel;Mark K Ho;Anna HarutyunyanThree Dogmas of Reinforcement Learning629-6442Matteo Papini;Giorgio Manganini;Alberto Maria Metelli;Marcello RestelliPolicy Gradient with Active Importance Sampling645-6752Riccardo Zamboni;Duilio Cirino;Marcello Restelli;Mirco MuttiThe Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough676-6922Zakariae EL ASRI;Olivier Sigaud;Nicolas THOMEPhysics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning693-7132Ho Long Fung;Victor-Alexandru Darvariu;Stephen Hailes;Mirco MusolesiTrust-based Consensus in Multi-Agent Reinforcement Learning Systems714-7322Yu Luo;Fuchun Sun;Tianying Ji;Xianyuan ZhanBidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies733-7622Gaspard Lambrechts;Adrien Bolland;Damien ErnstInformed POMDP: Leveraging Additional Information in Model-Based RL763-7842Sam Lobel;Ronald ParrAn Optimal Tightness Bound for the Simulation Lemma785-7972Milad Aghajohari;Tim Cooijmans;Juan Agustin Duque;Shunichi Akatsuka;Aaron CourvilleBest Response Shaping798-8182Gianluca Drappo;Alberto Maria Metelli;Marcello RestelliA Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning819-8392Khurram Javed;Arsalan Sharifnassab;Richard S. SuttonSwiftTD: A Fast and Robust Algorithm for Temporal Difference Learning840-8632Scott M. Jordan;Samuel Neumann;James E. Kostas;Adam White;Philip S. ThomasThe Cliff of Overcommitment with Policy Gradient Step Sizes864-8832Alexander Levine;Peter Stone;Amy ZhangMultistep Inverse Is Not All You Need884-9252Emma Cramer;Bernd Frauenknecht;Ramil Sabirov;Sebastian TrimpeContextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors926-9452Rohan Chitnis;Shentao Yang;Alborz GeramifardSequential Decision-Making for Inline Text Autocomplete946-9602Georgy Antonov;Peter DayanExploring Uncertainty in Distributional Reinforcement Learning961-9782Marcel Hussing;Jorge Mendez-Mendez;Anisha Singrodia;Cassandra Kent;Eric EatonRobotic Manipulation Datasets for Offline Compositional Reinforcement Learning979-9942Marcel Hussing;Claas A Voelcker;Igor Gilitschenski;Amir-massoud Farahmand;Eric EatonDissecting Deep RL with High Update Ratios: Combatting Value Divergence995-10182Brett Daley;Marlos C. Machado;Martha WhiteDemystifying the Recency Heuristic in Temporal-Difference Learning1019-10363Johan Samir Obando Ceron;João Guilherme Madeira Araújo;Aaron Courville;Pablo Samuel CastroOn the consistency of hyper-parameter selection in value-based deep reinforcement learning1037-10593Frieda Rong;Max Kleiman-WeinerValue Internalization: Learning and Generalizing from Social Reward1060-10713Timon Willi;Johan Samir Obando Ceron;Jakob Nicolaus Foerster;Gintare Karolina Dziugaite;Pablo Samuel CastroMixture of Experts in a Mixture of RL settings1072-11053Davide Corsi;Davide Camponogara;Alessandro FarinelliAquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning1106-11233Cyrus Cousins;Kavosh Asadi;Elita Lobo;Michael LittmanOn Welfare-Centric Fair Reinforcement Learning1124-11373Jiayu Yao;Weiwei Pan;Finale Doshi-Velez;Barbara E EngelhardtInverse Reinforcement Learning with Multiple Planning Horizons1138-11673Yixuan Zhang;Qiaomin XieConstant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation1168-12103Haque Ishfaq;Yixin Tan;Yu Yang;Qingfeng Lan;Jianfeng Lu;A. Rupam Mahmood;Doina Precup;Pan XuMore Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling1211-12353Qining Zhang;Honghao Wei;Lei YingReinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis1236-12513Kevin Tan;Ziping XuA Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage1252-12643Zhiyuan Zhou;Shreyas Sundara Raman;Henry Sowerby;Michael LittmanTiered Reward: Designing Rewards for Specification and Fast Learning of Desired Behavior1265-12883Bin Hu;Chenyang Zhao;Pu Zhang;Zihao Zhou;Yuanhang Yang;Zenglin Xu;Bin LiuEnabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach1289-13053Kris De Asis;Richard S. SuttonAn Idiosyncrasy of Time-discretization in Reinforcement Learning1306-13163Sai Prasanna;Karim Farid;Raghu Rajan;André BiedenkappDreaming of Many Worlds: Learning Contextual World Models aids Zero-Shot Generalization1317-13503Tetsuro Morimura;Kazuhiro Ota;Kenshi Abe;Peinan ZhangPolicy Gradient Algorithms with Monte Carlo Tree Learning for Non-Markov Decision Processes1351-13763Marin Vlastelica;Jin Cheng;Georg Martius;Pavel KolevOffline Diversity Maximization under Imitation Constraints1377-14093Léopold Maytié;Benjamin Devillers;Alexandre Arnold;Rufin VanRullenZero-shot cross-modal transfer of Reinforcement Learning policies through a Global Workspace1410-14263Motoki Omura;Takayuki Osa;YUSUKE Mukuta;Tatsuya HaradaStabilizing Extreme Q-learning by Maclaurin Expansion1427-14403Julian Dierkes;Emma Cramer;Holger Hoos;Sebastian TrimpeCombining Automated Optimisation of Hyperparameters and Reward Shape1441-14663He Wang;Laixi Shi;Yuejie ChiSample Complexity of Offline Distributionally Robust Linear Markov Decision Processes1467-15103Raphael Boige;Yannis Flet-Berliac;Lars C.P.M. Quaedvlieg;Arthur Flajolet;Guillaume Richard;Thomas PIERROTPASTA: Pretrained Action-State Transformer Agents1511-15323Kellen Kanarios;Qining Zhang;Lei YingCost Aware Best Arm Identification1533-15454Kartik Choudhary;Dhawal Gupta;Philip S. ThomasICU-Sepsis: A Benchmark MDP Built from Real Medical Data1546-15664Claas A Voelcker;Tyler Kastner;Igor Gilitschenski;Amir-massoud FarahmandWhen does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning1567-15974Changling Li;Zhang-Wei Hong;Pulkit Agrawal;Divyansh Garg;Joni PajarinenROER: Regularized Optimal Experience Replay1598-16184Philipp Becker;Sebastian Mossburger;Fabian Otto;Gerhard NeumannCombining Reconstruction and Contrastive Methods for Multimodal Representations in RL1619-16554Owen Oertell;Jonathan Daniel Chang;Yiyi Zhang;Kianté Brantley;Wen SunRL for Consistency Models: Reward Guided Text-to-Image Generation with Fast Inference1656-16734Miguel Vasco;Takuma Seno;Kenta Kawamoto;Kaushik Subramanian;Peter R. Wurman;Peter StoneA Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo1674-17104Miguel Suau;Matthijs T. J. Spaan;Frans A OliehoekBad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL1711-17324Rafael Rodriguez-Sanchez;George KonidarisLearning Abstract World Models for Value-preserving Planning with Options1733-17584Davide Corsi;Guy Amir;Andoni Rodríguez;Guy Katz;César Sánchez;Roy FoxVerification-Guided Shielding for Deep Reinforcement Learning1759-17804Forest Agostinelli;Misagh SoltaniLearning Discrete World Models for Heuristic Search1781-17924Zhengfei Zhang;Kishan Panaganti;Laixi Shi;Yanan Sui;Adam Wierman;Yisong YueDistributionally Robust Constrained Reinforcement Learning under Strong Duality1793-18214Connor Mattson;Anurag Sidharth Aribandi;Daniel S. BrownRepresentation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations1822-18404Gautham Vasan;Yan Wang;Fahim Shahriar;James Bergstra;Martin Jägersand;A. Rupam MahmoodRevisiting Sparse Rewards for Goal-Reaching Reinforcement Learning1841-18544Matthew Thomas Jackson;Michael Matthews;Cong Lu;Benjamin Ellis;Shimon Whiteson;Jakob Nicolaus FoersterPolicy-Guided Diffusion1855-18724James Staley;Elaine Short;Shivam Goel;Yash ShuklaAgent-Centric Human Demonstrations Train World Models1873-18864Akansha Kalra;Daniel S. BrownCan Differentiable Decision Trees Enable Interpretable Reward Learning from Human Feedback?1887-19104Wei-Di Chang;Scott Fujimoto;David Meger;Gregory DudekImitation Learning from Observation through Optimal Transport1911-19234Wancong Zhang;Anthony GX-Chen;Vlad Sobal;Yann LeCun;Nicolas CarionLight-weight Probing of Unsupervised Representations for Reinforcement Learning1924-19494Yuxin Chen;Chen Tang;Thomas Tian;Chenran Li;Jinning Li;Masayoshi Tomizuka;Wei ZhanQuantifying Interaction Level Between Agents Helps Cost-efficient Generalization in Multi-agent Reinforcement Learning1950-19644Daniel Melcer;Christopher Amato;Stavros TripakisShield Decomposition for Safe Reinforcement Learning in General Partially Observable Multi-Agent Environments1965-19944Abhishek Naik;Yi Wan;Manan Tomar;Richard S. SuttonReward Centering1995-20164Jan de Priester;Zachary Bell;Prashant Ganesh;Ricardo SanfeliceMultiHyRL: Robust Hybrid RL for Obstacle Avoidance against Adversarial Attacks on the Observation Space2017-20404Parham Mohammad Panahi;Andrew Patterson;Martha White;Adam WhiteInvestigating the Interplay of Prioritized Replay and Generalization2041-20585Bram M. Renting;Thomas M. Moerland;Holger Hoos;Catholijn M JonkerTowards General Negotiation Strategies with End-to-End Reinforcement Learning2059-20705Mark Bedaywi;Amin Rakhsha;Amir-massoud FarahmandPID Accelerated Temporal Difference Algorithms2071-20955Nadav Amir;Yael Niv;Angela J LangdonStates as goal-directed concepts: an epistemic approach to state-representation learning2096-21065Wanqiao Xu;Shi Dong;Benjamin Van RoyPosterior Sampling for Continuing Environments2107-21225Armin Karamzade;Kyungmin Kim;Montek Kalsi;Roy FoxReinforcement Learning from Delayed Observations via World Models2123-21395Johannes Ackermann;Takayuki Osa;Masashi SugiyamaOffline Reinforcement Learning from Datasets with Structured Non-Stationarity2140-21615Olivia P. Dizon-Paradis;Stephen E. Wormald;Daniel E. Capecci;Avanti Bhandarkar;Damon L. WoodardResource Usage Evaluation of Discrete Model-Free Deep Reinforcement Learning Algorithms2162-21775Rafael Rafailov;Kyle Beltran Hatch;Anikait Singh;Aviral Kumar;Laura Smith;Ilya Kostrikov;Philippe Hansen-Estruch;Victor Kolev;Philip J. Ball;Jiajun Wu;Sergey Levine;Chelsea FinnD5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning2178-21975Mohamed Elsayed;Qingfeng Lan;Clare Lyle;A. Rupam MahmoodWeight Clipping for Deep Continual and Reinforcement Learning2198-22175Sotetsu Koyamada;Soichiro Nishimori;Shin IshiiA Batch Sequential Halving Algorithm without Performance Degradation2218-22325Rahul Madhavan;Aurghya Maiti;Gaurav Sinha;Siddharth BarmanCausal Contextual Bandits with Adaptive Context2233-22635Allan Zhou;Vikash Kumar;Chelsea Finn;Aravind RajeswaranPolicy Architectures for Compositional Generalization in Control2264-22835Philipp Wu;Kourosh Hakhamaneshi;Yuqing Du;Igor Mordatch;Aravind Rajeswaran;Pieter AbbeelSemi-Supervised One Shot Imitation Learning2284-22975Andrew Patterson;Samuel Neumann;Raksha Kumaraswamy;Martha White;Adam WhiteCross-environment Hyperparameter Tuning for Reinforcement Learning2298-23195Daphne Cornelisse;Eugene VinitskyHuman-compatible driving agents through data-regularized self-play reinforcement learning2320-23445Jeremy McMahan;Young Wu;Yudong Chen;Jerry Zhu;Qiaomin XieInception: Efficiently Computable Misinformation Attacks on Markov Games2345-23585Linfeng Zhao;Lawson L.S. WongLearning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps2359-23725Jacob Adamczyk;Volodymyr Makarenko;Stas Tiomkin;Rahul V KulkarniBoosting Soft Q-Learning by Bounding2373-23995Hassan SABER;Odalric-Ambrym MaillardBandits with Multimodal Structure2400-24395Erin J Talvitie;Zilei Shao;Huiying Li;Jinghan Hu;Jacob Boerma;Rory Zhao;Xintong WangBounding-Box Inference for Error-Aware Model-Based Reinforcement Learning2440-24605Javad Azizi;Thang Duong;Yasin Abbasi-Yadkori;András György;Claire Vernade;Mohammad GhavamzadehNon-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms2461-24915Christopher Zeitler;Kristina Miller;Sayan Mitra;John Schierman;Mahesh ViswanathanOptimizing Rewards while meeting $\omega$-regular Constraints2492-25145