{"total":220,"rows":[{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107,"area":"wm"},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70,"area":null},{"id":"2402.06596","title":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","created":"2024-02-09","cited_by_count":60,"area":"agents"},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2107.10201","title":"Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs","created":"2021-07-21","cited_by_count":43,"area":null},{"id":"2205.05138","title":"Efficient Risk-Averse Reinforcement Learning","created":"2022-05-10","cited_by_count":43,"area":null},{"id":"2104.05632","title":"Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment","created":"2021-04-12","cited_by_count":42,"area":"wm"},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2205.13881","title":"Automated Dynamic Algorithm Configuration","created":"2022-05-27","cited_by_count":39,"area":null},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38,"area":null},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2408.07060","title":"Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents","created":"2024-08-13","cited_by_count":36,"area":"agents"},{"id":"2202.03060","title":"The Importance of Non-Markovianity in Maximum State Entropy Exploration","created":"2022-02-07","cited_by_count":35,"area":null},{"id":"2208.02225","title":"Sequence Model Imitation Learning with Unobserved Contexts","created":"2022-08-03","cited_by_count":34,"area":"offlinerl"},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31,"area":"deeprl"},{"id":"2203.16582","title":"Factored Adaptation for Non-Stationary Reinforcement Learning","created":"2022-03-30","cited_by_count":30,"area":null},{"id":"2105.08541","title":"DACBench: A Benchmark Library for Dynamic Algorithm Configuration","created":"2021-05-18","cited_by_count":28,"area":null},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2106.05110","title":"Self-Paced Context Evaluation for Contextual Reinforcement Learning","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2106.05262","title":"TempoRL: Learning When to Act","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2110.06972","title":"Block Contextual MDPs for Continual Learning","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2307.07907","title":"Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation","created":"2023-07-15","cited_by_count":25,"area":null},{"id":"2302.11070","title":"Universal Morphology Control via Contextual Modulation","created":"2023-02-22","cited_by_count":23,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21,"area":null},{"id":"2210.15629","title":"Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks","created":"2022-10-27","cited_by_count":20,"area":"diffusion"},{"id":"2306.03236","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2310.16686","title":"Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies","created":"2023-10-25","cited_by_count":20,"area":null},{"id":"2202.00104","title":"Generalization in Cooperative Multi-Agent Systems","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2211.15457","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":19,"area":null},{"id":"2202.07013","title":"Robust Policy Learning over Multiple Uncertainty Sets","created":"2022-02-14","cited_by_count":18,"area":null},{"id":"2112.08746","title":"Unsupervised Reinforcement Learning in Multiple Environments","created":"2021-12-16","cited_by_count":17,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2402.02429","title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","created":"2024-02-04","cited_by_count":17,"area":"offlinerl"},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2401.03374","title":"LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward","created":"2024-01-07","cited_by_count":16,"area":null},{"id":"2403.10967","title":"Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization","created":"2024-03-16","cited_by_count":16,"area":"wm"},{"id":"2110.03743","title":"Reinforcement Learning in Reward-Mixing MDPs","created":"2021-10-07","cited_by_count":15,"area":"alignment"},{"id":"2201.11211","title":"Learning Mixtures of Linear Dynamical Systems","created":"2022-01-26","cited_by_count":15,"area":null},{"id":"2212.12735","title":"An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context","created":"2022-12-24","cited_by_count":15,"area":null},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2503.00870","title":"NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains","created":"2025-03-02","cited_by_count":15,"area":null},{"id":"2110.06539","title":"On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning","created":"2021-10-13","cited_by_count":14,"area":"offlinerl"},{"id":"2406.01575","title":"Contextual Bilevel Reinforcement Learning for Incentive Alignment","created":"2024-06-03","cited_by_count":14,"area":"alignment"},{"id":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"1905.09710","title":"Inverse Reinforcement Learning in Contextual MDPs","created":"2019-05-23","cited_by_count":12,"area":"offlinerl"},{"id":"2305.15695","title":"Asking Before Acting: Gather Information in Embodied Decision Making with Language Models","created":"2023-05-25","cited_by_count":12,"area":null},{"id":"2202.03259","title":"Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration","created":"2022-02-07","cited_by_count":11,"area":null},{"id":"2205.13225","title":"DevFormer: A Symmetric Transformer for Context-Aware Device Placement","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2207.11126","title":"Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDP","created":"2022-07-22","cited_by_count":11,"area":null},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11,"area":null},{"id":"2402.06570","title":"Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control","created":"2024-02-09","cited_by_count":11,"area":null},{"id":"2203.00995","title":"Learning Efficiently Function Approximation for Contextual MDP","created":"2022-03-02","cited_by_count":10,"area":null},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2401.07031","title":"Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models","created":"2024-01-13","cited_by_count":10,"area":null},{"id":"2104.11707","title":"DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies","created":"2021-04-23","cited_by_count":9,"area":null},{"id":"2202.06557","title":"Reinforcement Learning in Presence of Discrete Markovian Context Evolution","created":"2022-02-14","cited_by_count":9,"area":null},{"id":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2303.01464","title":"Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2310.17769","title":"Social Contract AI: Aligning AI Assistants with Implicit Group Norms","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2405.14073","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","created":"2024-05-23","cited_by_count":9,"area":"deeprl"},{"id":"2504.13145","title":"Exploring Expert Failures Improves LLM Agent Tuning","created":"2025-04-17","cited_by_count":9,"area":"agents"},{"id":"2205.12381","title":"First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization","created":"2022-05-24","cited_by_count":8,"area":null},{"id":"2405.17796","title":"Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2412.10419","title":"Preference Adaptive and Sequential Text-to-Image Generation","created":"2024-12-10","cited_by_count":8,"area":"deeprl"},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2506.18631","title":"ReDit: Reward Dithering for Improved LLM Policy Optimization","created":"2025-06-23","cited_by_count":8,"area":"lr"},{"id":"2109.11792","title":"Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability","created":"2021-09-24","cited_by_count":7,"area":null},{"id":"2210.12262","title":"Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2405.02481","title":"Proximal Curriculum with Task Correlations for Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":7,"area":"deeprl"},{"id":"2408.04498","title":"Model-Based Transfer Learning for Contextual Reinforcement Learning","created":"2024-08-08","cited_by_count":7,"area":"deeprl"},{"id":"2410.15221","title":"IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning","created":"2024-10-19","cited_by_count":7,"area":"driving"},{"id":"2302.02182","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2305.13747","title":"Optimizing Long-term Value for Auction-Based Recommender Systems via On-Policy Reinforcement Learning","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2309.14091","title":"On the Benefit of Optimal Transport for Curriculum Reinforcement Learning","created":"2023-09-25","cited_by_count":6,"area":null},{"id":"2310.18803","title":"Weakly Coupled Deep Q-Networks","created":"2023-10-28","cited_by_count":6,"area":null},{"id":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2504.20887","title":"Return Capping: Sample-Efficient CVaR Policy Gradient Optimisation","created":"2025-04-29","cited_by_count":6,"area":"deeprl"},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2603.07432","title":"Generalization in Online Reinforcement Learning for Mobile Agents","created":"2026-03-08","cited_by_count":6,"area":"lr"},{"id":"2112.06625","title":"Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization","created":"2021-12-13","cited_by_count":5,"area":null},{"id":"2210.02594","title":"Reward-Mixing MDPs with a Few Latent Contexts are Learnable","created":"2022-10-05","cited_by_count":5,"area":"alignment"},{"id":"2402.02700","title":"Sample Complexity Characterization for Linear Contextual MDPs","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2404.09521","title":"Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning","created":"2024-04-15","cited_by_count":5,"area":"deeprl"},{"id":"2501.06366","title":"Counterfactually Fair Reinforcement Learning via Sequential Data Preprocessing","created":"2025-01-10","cited_by_count":5,"area":"deeprl"},{"id":"2502.20265","title":"On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+($\\lambda$,$\\lambda$))-GA","created":"2025-02-27","cited_by_count":5,"area":"deeprl"},{"id":"2508.20294","title":"Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization","created":"2025-08-27","cited_by_count":5,"area":"wm"},{"id":"2511.09737","title":"Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single Policy","created":"2025-11-12","cited_by_count":5,"area":null},{"id":"2106.03833","title":"Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement Learning","created":"2021-06-07","cited_by_count":4,"area":"offlinerl"},{"id":"2210.11604","title":"Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2212.10876","title":"Hyperparameters in Contextual RL are Highly Situational","created":"2022-12-21","cited_by_count":4,"area":null}],"next_cursor":"100"}