{"total":82,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"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":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86,"area":"deeprl"},{"id":"2307.03659","title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","created":"2023-07-07","cited_by_count":82,"area":"offlinerl"},{"id":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63,"area":"offlinerl"},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39,"area":null},{"id":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34,"area":null},{"id":"2102.13268","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","created":"2021-02-26","cited_by_count":31,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"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":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25,"area":null},{"id":"2206.05266","title":"Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?","created":"2022-06-10","cited_by_count":24,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2106.02193","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2206.12984","title":"Improving Policy Optimization with Generalist-Specialist Learning","created":"2022-06-26","cited_by_count":20,"area":null},{"id":"2306.03072","title":"Explore to Generalize in Zero-Shot RL","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2209.13841","title":"Online Policy Optimization for Robust MDP","created":"2022-09-28","cited_by_count":19,"area":null},{"id":"2111.14629","title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions","created":"2021-11-29","cited_by_count":17,"area":"offlinerl"},{"id":"2409.04792","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","created":"2024-09-07","cited_by_count":17,"area":"deeprl"},{"id":"2106.15587","title":"Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14,"area":null},{"id":"2210.17375","title":"ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation","created":"2022-10-26","cited_by_count":14,"area":null},{"id":"2301.10886","title":"Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning","created":"2023-01-26","cited_by_count":12,"area":null},{"id":"2209.14940","title":"Reinforcement Learning Algorithms: An Overview and Classification","created":"2022-09-29","cited_by_count":10,"area":null},{"id":"2204.06355","title":"Local Feature Swapping for Generalization in Reinforcement Learning","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2408.03195","title":"RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning","created":"2024-08-06","cited_by_count":9,"area":"deeprl"},{"id":"2603.00977","title":"HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents","created":"2026-03-01","cited_by_count":9,"area":"agents"},{"id":"2106.15883","title":"Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2210.09960","title":"Rethinking Value Function Learning for Generalization in Reinforcement Learning","created":"2022-10-18","cited_by_count":8,"area":null},{"id":"2303.05069","title":"Conceptual Reinforcement Learning for Language-Conditioned Tasks","created":"2023-03-09","cited_by_count":8,"area":null},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","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":"2503.06343","title":"Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning","created":"2025-03-08","cited_by_count":8,"area":"deeprl"},{"id":"2304.10770","title":"DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2410.10905","title":"Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale","created":"2024-10-13","cited_by_count":6,"area":"deeprl"},{"id":"2503.05546","title":"Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning","created":"2025-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2303.05092","title":"Task Aware Dreamer for Task Generalization in Reinforcement Learning","created":"2023-03-09","cited_by_count":5,"area":"wm"},{"id":"2510.21609","title":"Enhancing Tactile-based Reinforcement Learning for Robotic Control","created":"2025-10-24","cited_by_count":5,"area":"deeprl"},{"id":"2106.02229","title":"Differentiable Architecture Search for Reinforcement Learning","created":"2021-06-04","cited_by_count":4,"area":null},{"id":"2207.06105","title":"GriddlyJS: A Web IDE for Reinforcement Learning","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2302.09601","title":"Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution","created":"2023-02-19","cited_by_count":4,"area":null},{"id":"2309.16382","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2504.05152","title":"PanoDreamer: Consistent Text to 360-Degree Scene Generation","created":"2025-04-07","cited_by_count":3,"area":null},{"id":"2512.08763","title":"Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning","created":"2025-12-09","cited_by_count":3,"area":"deeprl"},{"id":"2206.10027","title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","created":"2022-06-20","cited_by_count":2,"area":null},{"id":"2308.15550","title":"Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning","created":"2023-08-29","cited_by_count":2,"area":null},{"id":"2105.03923","title":"CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration","created":"2021-05-09","cited_by_count":1,"area":null},{"id":"2204.04292","title":"Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2208.02376","title":"AACC: Asymmetric Actor-Critic in Contextual Reinforcement Learning","created":"2022-08-03","cited_by_count":1,"area":null},{"id":"2210.02224","title":"Neural Distillation as a State Representation Bottleneck in Reinforcement Learning","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2210.04209","title":"Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning","created":"2022-10-09","cited_by_count":1,"area":null},{"id":"2304.09825","title":"Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments","created":"2023-04-18","cited_by_count":1,"area":"offlinerl"},{"id":"2501.02481","title":"Representation Convergence: Mutual Distillation is Secretly a Form of Regularization","created":"2025-01-05","cited_by_count":1,"area":"deeprl"},{"id":"2501.12620","title":"Adaptive Data Exploitation in Deep Reinforcement Learning","created":"2025-01-22","cited_by_count":1,"area":"deeprl"},{"id":"2501.17384","title":"A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning","created":"2025-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2502.08336","title":"Salience-Invariant Consistent Policy Learning for Generalization in Visual Reinforcement Learning","created":"2025-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2503.01146","title":"Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario Augmentation","created":"2025-03-03","cited_by_count":1,"area":"deeprl"},{"id":"2508.01329","title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","created":"2025-08-02","cited_by_count":1,"area":"deeprl"},{"id":"2510.24194","title":"Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames","created":"2025-10-28","cited_by_count":1,"area":"offlinerl"},{"id":"2203.13125","title":"Intelligent Systematic Investment Agent: an ensemble of deep learning and evolutionary strategies","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2305.19035","title":"Solving Robust MDPs through No-Regret Dynamics","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2311.00426","title":"Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards","created":"2023-11-01","cited_by_count":0,"area":null},{"id":"2403.07979","title":"Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning","created":"2024-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2407.13146","title":"PG-Rainbow: Using Distributional Reinforcement Learning in Policy Gradient Methods","created":"2024-07-18","cited_by_count":0,"area":"deeprl"},{"id":"2409.13108","title":"Disentangling Recognition and Decision Regrets in Image-Based Reinforcement Learning","created":"2024-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2503.08867","title":"Zero-Shot Action Generalization with Limited Observations","created":"2025-03-11","cited_by_count":0,"area":"deeprl"},{"id":"2506.11912","title":"Breaking Habits: On the Role of the Advantage Function in Learning Causal State Representations","created":"2025-06-13","cited_by_count":0,"area":"deeprl"},{"id":"2508.12356","title":"Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data","created":"2025-08-17","cited_by_count":0,"area":"offlinerl"},{"id":"2509.00347","title":"LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning","created":"2025-08-30","cited_by_count":0,"area":"offlinerl"},{"id":"2512.22824","title":"TEACH: Temporal Variance-Driven Curriculum for Reinforcement Learning","created":"2025-12-28","cited_by_count":0,"area":"deeprl"},{"id":"2601.14232","title":"KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning","created":"2026-01-20","cited_by_count":0,"area":"deeprl"},{"id":"2602.19956","title":"Sparse Masked Attention Policies for Reliable Generalization","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2603.27515","title":"Match or Replay: Self Imitating Proximal Policy Optimization","created":"2026-03-29","cited_by_count":0,"area":"deeprl"},{"id":"2604.25534","title":"Sample-efficient Neuro-symbolic Proximal Policy Optimization","created":"2026-04-28","cited_by_count":0,"area":"deeprl"},{"id":"2606.16236","title":"Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2608.26481","title":"Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement Learning","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.01811","title":"Reinforcement learning to choose optimizers","created":"2026-09-01","cited_by_count":0,"area":"deeprl"},{"id":"2609.32532","title":"What Does a ProcGen Generalization Gap Measure? Action Rules, Residual Entropy, and the Missing Random Floor","created":"2026-09-26","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}