{"total":118,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566,"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":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144,"area":"deeprl"},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143,"area":"alignment"},{"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":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121,"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":"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":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73,"area":"offlinerl"},{"id":"2107.02053","title":"MixStyle Neural Networks for Domain Generalization and Adaptation","created":"2021-07-05","cited_by_count":64,"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":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2312.12444","title":"What Makes Pre-Trained Visual Representations Successful for Robust Manipulation?","created":"2023-11-03","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":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"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":"2102.13268","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","created":"2021-02-26","cited_by_count":31,"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":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30,"area":"lr"},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2109.03214","title":"Robust Predictable Control","created":"2021-09-07","cited_by_count":29,"area":null},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2402.15399","title":"Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation","created":"2024-02-23","cited_by_count":25,"area":"deeprl"},{"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":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2105.05347","title":"Return-based Scaling: Yet Another Normalisation Trick for Deep RL","created":"2021-05-11","cited_by_count":23,"area":null},{"id":"2209.12016","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","created":"2022-09-24","cited_by_count":21,"area":null},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","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":"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":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2108.01005","title":"Sequoia: A Software Framework to Unify Continual Learning Research","created":"2021-08-02","cited_by_count":19,"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":"2403.09621","title":"Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning","created":"2024-03-14","cited_by_count":18,"area":"offlinerl"},{"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":"2403.05996","title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","created":"2024-03-09","cited_by_count":17,"area":"deeprl"},{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"area":"deeprl"},{"id":"2202.05404","title":"Regularized Q-learning","created":"2022-02-11","cited_by_count":16,"area":null},{"id":"2409.20521","title":"Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning","created":"2024-09-30","cited_by_count":16,"area":"deeprl"},{"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":"2410.11689","title":"BlendRL: A Framework for Merging Symbolic and Neural Policy Learning","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2106.03955","title":"Correcting Momentum in Temporal Difference Learning","created":"2021-06-07","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":"2406.03997","title":"HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning","created":"2024-06-06","cited_by_count":11,"area":"deeprl"},{"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":"2506.05982","title":"MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks","created":"2025-06-06","cited_by_count":11,"area":null},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2202.11818","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","created":"2022-02-23","cited_by_count":10,"area":null},{"id":"2312.15339","title":"MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2401.17835","title":"Simplifying Latent Dynamics with Softly State-Invariant World Models","created":"2024-01-31","cited_by_count":10,"area":"wm"},{"id":"2204.06355","title":"Local Feature Swapping for Generalization in Reinforcement Learning","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2104.07750","title":"Joint Attention for Multi-Agent Coordination and Social Learning","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2105.02331","title":"Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance","created":"2021-05-05","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":"2106.02613","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2210.10464","title":"On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness","created":"2022-10-19","cited_by_count":7,"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":"2504.10865","title":"Understanding the theoretical properties of projected Bellman equation, linear Q-learning, and approximate value iteration","created":"2025-04-15","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":"2307.04887","title":"Measuring and Mitigating Interference in Reinforcement Learning","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2408.08761","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","created":"2024-08-16","cited_by_count":5,"area":"deeprl"},{"id":"2410.23810","title":"CALE: Continuous Arcade Learning Environment","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2207.06105","title":"GriddlyJS: A Web IDE for Reinforcement Learning","created":"2022-07-13","cited_by_count":4,"area":null},{"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":"2210.12448","title":"Probing Transfer in Deep Reinforcement Learning without Task Engineering","created":"2022-10-22","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":"2406.06037","title":"Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning","created":"2024-06-10","cited_by_count":4,"area":"deeprl"},{"id":"2102.08581","title":"Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning","created":"2021-02-17","cited_by_count":3,"area":null},{"id":"2110.02639","title":"On The Transferability of Deep-Q Networks","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2304.01366","title":"Enabling A Network AI Gym for Autonomous Cyber Agents","created":"2023-04-03","cited_by_count":3,"area":null},{"id":"2306.06251","title":"Design Principles for Model Generalization and Scalable AI Integration in Radio Access Networks","created":"2023-06-09","cited_by_count":3,"area":null},{"id":"2407.15656","title":"Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN","created":"2024-07-22","cited_by_count":3,"area":"deeprl"},{"id":"2408.07644","title":"SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning","created":"2024-08-14","cited_by_count":3,"area":null},{"id":"2507.06602","title":"Generalization in Reinforcement Learning for Radio Access Networks","created":"2025-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2510.16175","title":"The Formalism-Implementation Gap in Reinforcement Learning Research","created":"2025-10-17","cited_by_count":3,"area":"deeprl"},{"id":"2609.16679","title":"AI for Games in the Foundation Model Era","created":"2026-09-15","cited_by_count":3,"area":"wm"},{"id":"2102.04220","title":"Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning","created":"2021-02-08","cited_by_count":2,"area":null},{"id":"2103.08070","title":"Learning robust driving policies without online exploration","created":"2021-03-15","cited_by_count":2,"area":"driving"},{"id":"2402.09290","title":"Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning","created":"2024-02-14","cited_by_count":2,"area":"deeprl"},{"id":"2406.01952","title":"Improving Generalization in Aerial and Terrestrial Mobile Robots Control Through Delayed Policy Learning","created":"2024-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2407.20651","title":"Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations","created":"2024-07-30","cited_by_count":2,"area":"deeprl"},{"id":"2504.03024","title":"Deep Reinforcement Learning via Object-Centric Attention","created":"2025-04-03","cited_by_count":2,"area":"deeprl"},{"id":"2508.06871","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","created":"2025-08-09","cited_by_count":2,"area":"deeprl"},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2204.07254","title":"Methodical Advice Collection and Reuse in Deep Reinforcement Learning","created":"2022-04-14","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":"2302.04151","title":"Policy Evaluation in Decentralized POMDPs with Belief Sharing","created":"2023-02-08","cited_by_count":1,"area":null},{"id":"2304.01244","title":"Unified Emulation-Simulation Training Environment for Autonomous Cyber Agents","created":"2023-04-03","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":"2501.02481","title":"Representation Convergence: Mutual Distillation is Secretly a Form of Regularization","created":"2025-01-05","cited_by_count":1,"area":"deeprl"}],"next_cursor":"100"}