{"total":118,"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":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237,"area":"wm"},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200,"area":null},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174,"area":null},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174,"area":null},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2303.07109","title":"Transformer-based World Models Are Happy With 100k Interactions","created":"2023-03-13","cited_by_count":139,"area":"wm"},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112,"area":null},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2310.09615","title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","created":"2023-10-14","cited_by_count":89,"area":"wm"},{"id":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78,"area":"moe"},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"2106.04615","title":"Vector Quantized Models for Planning","created":"2021-06-08","cited_by_count":48,"area":null},{"id":"2110.00188","title":"Offline Reinforcement Learning with Reverse Model-based Imagination","created":"2021-10-01","cited_by_count":47,"area":"offlinerl"},{"id":"2106.04379","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":44,"area":null},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2106.04152","title":"PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning","created":"2021-06-08","cited_by_count":41,"area":null},{"id":"2201.12096","title":"Mask-based Latent Reconstruction for Reinforcement Learning","created":"2022-01-28","cited_by_count":39,"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":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36,"area":null},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2106.15434","title":"Zoo-Tuning: Adaptive Transfer from a Zoo of Models","created":"2021-06-29","cited_by_count":35,"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":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2207.14800","title":"Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning","created":"2022-07-29","cited_by_count":26,"area":null},{"id":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25,"area":null},{"id":"2111.07775","title":"Learning Representations for Pixel-based Control: What Matters and Why?","created":"2021-11-15","cited_by_count":24,"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":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21,"area":"deeprl"},{"id":"2206.03271","title":"On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning","created":"2022-06-07","cited_by_count":19,"area":null},{"id":"2502.07523","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","created":"2025-02-11","cited_by_count":19,"area":"deeprl"},{"id":"2203.15845","title":"Topological Experience Replay","created":"2022-03-29","cited_by_count":17,"area":null},{"id":"2211.02222","title":"The Benefits of Model-Based Generalization in Reinforcement Learning","created":"2022-11-04","cited_by_count":17,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2206.04551","title":"A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning","created":"2022-06-09","cited_by_count":15,"area":null},{"id":"2206.12542","title":"Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning","created":"2022-06-25","cited_by_count":15,"area":null},{"id":"2410.01930","title":"Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL","created":"2024-10-02","cited_by_count":14,"area":"deeprl"},{"id":"2209.07670","title":"Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks","created":"2022-09-16","cited_by_count":13,"area":null},{"id":"2210.06041","title":"Reinforcement Learning with Automated Auxiliary Loss Search","created":"2022-10-12","cited_by_count":13,"area":null},{"id":"2502.01591","title":"Improving Transformer World Models for Data-Efficient RL","created":"2025-02-03","cited_by_count":13,"area":"wm"},{"id":"2103.02886","title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","created":"2021-03-04","cited_by_count":12,"area":null},{"id":"2206.02902","title":"Goal-Space Planning with Subgoal Models","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2210.12719","title":"Learning General World Models in a Handful of Reward-Free Deployments","created":"2022-10-23","cited_by_count":12,"area":"wm"},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2506.17204","title":"Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":11,"area":"deeprl"},{"id":"2111.10247","title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","created":"2021-11-19","cited_by_count":10,"area":null},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","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":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2205.14557","title":"Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning","created":"2022-05-29","cited_by_count":8,"area":null},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2306.00840","title":"What model does MuZero learn?","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2302.07160","title":"Learning a model is paramount for sample efficiency in reinforcement learning control of PDEs","created":"2023-02-14","cited_by_count":6,"area":null},{"id":"2402.10228","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","created":"2024-02-05","cited_by_count":6,"area":"deeprl"},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2107.05405","title":"Learning Expected Emphatic Traces for Deep RL","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2206.03726","title":"Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models","created":"2022-06-08","cited_by_count":5,"area":null},{"id":"2206.08442","title":"A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings","created":"2022-06-16","cited_by_count":5,"area":null},{"id":"2209.10901","title":"Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning","created":"2022-09-22","cited_by_count":5,"area":null},{"id":"2301.11426","title":"Model-based Offline Reinforcement Learning with Local Misspecification","created":"2023-01-26","cited_by_count":5,"area":"offlinerl"},{"id":"2303.01668","title":"RePreM: Representation Pre-training with Masked Model for Reinforcement Learning","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2407.09702","title":"Investigating the Interplay of Prioritized Replay and Generalization","created":"2024-07-12","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":"2502.07937","title":"Active Advantage-Aligned Online Reinforcement Learning with Offline Data","created":"2025-02-11","cited_by_count":5,"area":"offlinerl"},{"id":"2102.06782","title":"Q-Value Weighted Regression: Reinforcement Learning with Limited Data","created":"2021-02-12","cited_by_count":4,"area":null},{"id":"2202.09699","title":"Selective Credit Assignment","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2205.00943","title":"CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning","created":"2022-05-02","cited_by_count":4,"area":null},{"id":"2207.02518","title":"Compositional Generalization in Grounded Language Learning via Induced Model Sparsity","created":"2022-07-06","cited_by_count":4,"area":null},{"id":"2305.13185","title":"Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2505.17749","title":"Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning","created":"2025-05-23","cited_by_count":4,"area":"deeprl"},{"id":"2409.02714","title":"MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning","created":"2024-09-02","cited_by_count":3,"area":"deeprl"},{"id":"2410.05782","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","created":"2024-10-08","cited_by_count":3,"area":"alignment"},{"id":"2506.02612","title":"Simple, Good, Fast: Self-Supervised World Models Free of Baggage","created":"2025-06-03","cited_by_count":3,"area":"wm"},{"id":"2510.16175","title":"The Formalism-Implementation Gap in Reinforcement Learning Research","created":"2025-10-17","cited_by_count":3,"area":"deeprl"},{"id":"2107.01904","title":"Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning","created":"2021-07-05","cited_by_count":2,"area":null},{"id":"2202.01534","title":"Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems","created":"2022-02-03","cited_by_count":2,"area":null},{"id":"2203.03078","title":"Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation","created":"2022-03-07","cited_by_count":2,"area":null},{"id":"2205.09869","title":"Transformer with Memory Replay","created":"2022-05-19","cited_by_count":2,"area":null},{"id":"2304.09718","title":"Sample-efficient Model-based Reinforcement Learning for Quantum Control","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2305.12216","title":"On First-Order Meta-Reinforcement Learning with Moreau Envelopes","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2308.04263","title":"BarlowRL: Barlow Twins for Data-Efficient Reinforcement Learning","created":"2023-08-08","cited_by_count":2,"area":null},{"id":"2407.18840","title":"The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2102.03866","title":"Model-Augmented Q-learning","created":"2021-02-07","cited_by_count":1,"area":null},{"id":"2104.10483","title":"Adaptive learning for financial markets mixing model-based and model-free RL for volatility targeting","created":"2021-04-19","cited_by_count":1,"area":null},{"id":"2205.15824","title":"Graph Backup: Data Efficient Backup Exploiting Markovian Transitions","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2305.17623","title":"On the Value of Myopic Behavior in Policy Reuse","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2309.14243","title":"Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2405.03878","title":"Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning","created":"2024-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2408.10713","title":"Offline Model-Based Reinforcement Learning with Anti-Exploration","created":"2024-08-20","cited_by_count":1,"area":"offlinerl"},{"id":"2507.00275","title":"Deep Double Q-learning","created":"2025-06-30","cited_by_count":1,"area":"deeprl"},{"id":"2606.19357","title":"Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots","created":"2026-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2104.08543","title":"Planning with Expectation Models for Control","created":"2021-04-17","cited_by_count":0,"area":null},{"id":"2111.06907","title":"Improving Experience Replay through Modeling of Similar Transitions' Sets","created":"2021-11-12","cited_by_count":0,"area":null}],"next_cursor":"100"}