{"total":91,"rows":[{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"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":"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":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105,"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":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"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":"2212.08860","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","created":"2022-12-17","cited_by_count":60,"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":"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":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"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":"2402.12479","title":"In value-based deep reinforcement learning, a pruned network is a good network","created":"2024-02-19","cited_by_count":39,"area":"deeprl"},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"area":"deeprl"},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36,"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":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","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":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25,"area":null},{"id":"2410.14972","title":"MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning","created":"2024-10-19","cited_by_count":23,"area":"moe"},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","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":"2209.13841","title":"Online Policy Optimization for Robust MDP","created":"2022-09-28","cited_by_count":19,"area":null},{"id":"2312.17227","title":"Gradient-based Planning with World Models","created":"2023-12-28","cited_by_count":19,"area":"wm"},{"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":"2308.10797","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary","created":"2023-08-21","cited_by_count":17,"area":null},{"id":"2211.11030","title":"Adversarial Cheap Talk","created":"2022-11-20","cited_by_count":16,"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":"2205.10218","title":"Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions","created":"2022-05-20","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":"2404.18926","title":"Point Cloud Models Improve Visual Robustness in Robotic Learners","created":"2024-04-29","cited_by_count":14,"area":null},{"id":"2105.13524","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"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":"2309.10790","title":"Guide Your Agent with Adaptive Multimodal Rewards","created":"2023-09-19","cited_by_count":10,"area":"offlinerl"},{"id":"2204.06355","title":"Local Feature Swapping for Generalization in Reinforcement Learning","created":"2022-04-13","cited_by_count":9,"area":null},{"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":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2410.10834","title":"Focus On What Matters: Separated Models For Visual-Based RL Generalization","created":"2024-09-29","cited_by_count":6,"area":"deeprl"},{"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":"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":"2302.09601","title":"Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution","created":"2023-02-19","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":"2505.08361","title":"Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning","created":"2025-05-13","cited_by_count":4,"area":"deeprl"},{"id":"2102.04353","title":"Unlocking Pixels for Reinforcement Learning via Implicit Attention","created":"2021-02-08","cited_by_count":3,"area":null},{"id":"2201.12300","title":"Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulation","created":"2022-01-28","cited_by_count":3,"area":null},{"id":"2305.04082","title":"A Minimal Approach for Natural Language Action Space in Text-based Games","created":"2023-05-06","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":"2102.10774","title":"Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning","created":"2021-02-22","cited_by_count":2,"area":"offlinerl"},{"id":"2210.09646","title":"RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning","created":"2022-10-18","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":"2409.08012","title":"Learning Causally Invariant Reward Functions from Diverse Demonstrations","created":"2024-09-12","cited_by_count":2,"area":"offlinerl"},{"id":"2502.05555","title":"Efficient Reinforcement Learning Through Adaptively Pretrained Visual Encoder","created":"2025-02-08","cited_by_count":2,"area":"deeprl"},{"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":"2311.07312","title":"C-Procgen: Empowering Procgen with Controllable Contexts","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2402.06682","title":"Private Knowledge Sharing in Distributed Learning: A Survey","created":"2024-02-08","cited_by_count":1,"area":null},{"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":"2501.17384","title":"A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning","created":"2025-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2601.21094","title":"Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed","created":"2026-01-28","cited_by_count":1,"area":"deeprl"},{"id":"2609.20820","title":"Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2203.10351","title":"The Sandbox Environment for Generalizable Agent Research (SEGAR)","created":"2022-03-19","cited_by_count":0,"area":null},{"id":"2204.14076","title":"Dynamic Noises of Multi-Agent Environments Can Improve Generalization: Agent-based Models meets Reinforcement Learning","created":"2022-03-26","cited_by_count":0,"area":null},{"id":"2210.07312","title":"Bootstrap Advantage Estimation for Policy Optimization in Reinforcement Learning","created":"2022-10-13","cited_by_count":0,"area":null},{"id":"2301.13473","title":"CRC-RL: A Novel Visual Feature Representation Architecture for Unsupervised Reinforcement Learning","created":"2023-01-31","cited_by_count":0,"area":null},{"id":"2302.06126","title":"Expediting Distributed DNN Training with Device Topology-Aware Graph Deployment","created":"2023-02-13","cited_by_count":0,"area":null},{"id":"2304.14533","title":"Adversarial Policy Optimization in Deep Reinforcement Learning","created":"2023-04-27","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":"2407.04064","title":"Collision Avoidance for Multiple UAVs in Unknown Scenarios with Causal Representation Disentanglement","created":"2024-07-04","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":"2411.15972","title":"Stability properties of gradient flow dynamics for the symmetric low-rank matrix factorization problem","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2502.07280","title":"MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management","created":"2025-02-11","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":"2507.11975","title":"Online Training and Pruning of Deep Reinforcement Learning Networks","created":"2025-07-16","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":"2511.20591","title":"Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning","created":"2025-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2605.10546","title":"Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning","created":"2026-05-11","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}