{"total":87,"rows":[{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173,"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":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123,"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":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111,"area":null},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109,"area":null},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"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":"2103.03216","title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","created":"2021-03-04","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":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2401.11237","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","created":"2024-01-20","cited_by_count":27,"area":"deeprl"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","created":"2023-12-20","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":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20,"area":null},{"id":"2210.10243","title":"CLUTR: Curriculum Learning via Unsupervised Task Representation Learning","created":"2022-10-19","cited_by_count":20,"area":null},{"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":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2308.10797","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary","created":"2023-08-21","cited_by_count":17,"area":null},{"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":"2312.17116","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","created":"2023-12-28","cited_by_count":12,"area":null},{"id":"2209.08660","title":"Learn the Time to Learn: Replay Scheduling in Continual Learning","created":"2022-09-18","cited_by_count":11,"area":null},{"id":"2406.17949","title":"The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design","created":"2024-06-25","cited_by_count":11,"area":"deeprl"},{"id":"2306.02419","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","created":"2023-06-04","cited_by_count":10,"area":null},{"id":"2410.19715","title":"Adversarial Environment Design via Regret-Guided Diffusion Models","created":"2024-10-25","cited_by_count":10,"area":"diffusion"},{"id":"2204.06355","title":"Local Feature Swapping for Generalization in Reinforcement Learning","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2301.08025","title":"Generalization through Diversity: Improving Unsupervised Environment Design","created":"2023-01-19","cited_by_count":9,"area":null},{"id":"2304.13424","title":"Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories","created":"2023-04-26","cited_by_count":9,"area":null},{"id":"2310.15017","title":"Mind the Model, Not the Agent: The Primacy Bias in Model-based RL","created":"2023-10-23","cited_by_count":9,"area":"wm"},{"id":"2112.00901","title":"Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL","created":"2021-12-02","cited_by_count":8,"area":null},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2402.05309","title":"Investigating Generalization Behaviours of Generative Flow Networks","created":"2024-02-07","cited_by_count":6,"area":null},{"id":"2406.15753","title":"The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret","created":"2024-06-22","cited_by_count":6,"area":"alignment"},{"id":"2307.11685","title":"Towards Generalizable Reinforcement Learning for Trade Execution","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2207.07749","title":"Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement Learning","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2303.10144","title":"Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting","created":"2023-03-17","cited_by_count":4,"area":"wm"},{"id":"2303.17655","title":"Q-Learning based system for path planning with unmanned aerial vehicles swarms in obstacle environments","created":"2023-03-30","cited_by_count":4,"area":null},{"id":"2402.07875","title":"Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States","created":"2024-02-12","cited_by_count":4,"area":"deeprl"},{"id":"2509.10423","title":"Mutual Information Tracks Policy Coherence in Reinforcement Learning","created":"2025-09-12","cited_by_count":4,"area":"deeprl"},{"id":"2102.11893","title":"Honey, I Shrunk The Actor: A Case Study on Preserving Performance with Smaller Actors in Actor-Critic RL","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2110.01833","title":"Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchies","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"id":"2504.10002","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions","created":"2025-04-14","cited_by_count":3,"area":"alignment"},{"id":"2507.06602","title":"Generalization in Reinforcement Learning for Radio Access Networks","created":"2025-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2106.03748","title":"Towards robust and domain agnostic reinforcement learning competitions","created":"2021-06-07","cited_by_count":2,"area":null},{"id":"2107.08888","title":"Multimodal Reward Shaping for Efficient Exploration in Reinforcement Learning","created":"2021-07-19","cited_by_count":2,"area":null},{"id":"2211.06733","title":"Deep Reinforcement Learning with Vector Quantized Encoding","created":"2022-11-12","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":"2102.07266","title":"Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning","created":"2021-02-14","cited_by_count":1,"area":null},{"id":"2311.07312","title":"C-Procgen: Empowering Procgen with Controllable Contexts","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2401.09258","title":"Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2404.04106","title":"Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical Report","created":"2024-04-05","cited_by_count":1,"area":"deeprl"},{"id":"2501.11136","title":"A Novel Switch-Type Policy Network for Resource Allocation Problems: Technical Report","created":"2025-01-19","cited_by_count":1,"area":"deeprl"},{"id":"2501.13241","title":"State Combinatorial Generalization In Decision Making With Conditional Diffusion Models","created":"2025-01-22","cited_by_count":1,"area":"diffusion"},{"id":"2601.14957","title":"Improving Regret Approximation for Unsupervised Dynamic Environment Generation","created":"2026-01-21","cited_by_count":1,"area":"deeprl"},{"id":"2204.02210","title":"Model Based Meta Learning of Critics for Policy Gradients","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2210.03850","title":"Information Topology","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2302.06009","title":"Policy-Induced Self-Supervision Improves Representation Finetuning in Visual RL","created":"2023-02-12","cited_by_count":0,"area":null},{"id":"2303.16266","title":"On-line reinforcement learning for optimization of real-life energy trading strategy","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2310.12494","title":"SDGym: Low-Code Reinforcement Learning Environments using System Dynamics Models","created":"2023-10-19","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":"2404.05484","title":"What is Intelligence? A Cycle Closure Perspective","created":"2024-04-08","cited_by_count":0,"area":null},{"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":"2412.16970","title":"A Research Agenda for Usability and Generalisation in Reinforcement Learning","created":"2024-12-22","cited_by_count":0,"area":"deeprl"},{"id":"2505.11100","title":"Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.08961","title":"Towards Robust Deep Reinforcement Learning against Environmental State Perturbation","created":"2025-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2604.08355","title":"ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.12206","title":"Train Short, Act Long: Multistability and the Horizon Independence of Recurrent Policies","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2607.07365","title":"Improving greenhouse fruit-production control by integrating reinforcement learning into short-horizon model predictive control","created":"2026-07-08","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}