{"total":785,"rows":[{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300,"area":"wm"},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237,"area":"wm"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187,"area":null},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174,"area":null},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"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":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"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":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"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":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"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":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2103.04000","title":"Off-Belief Learning","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"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":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"area":null},{"id":"2102.03479","title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-06","cited_by_count":68,"area":null},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2101.01993","title":"A Survey of Deep RL and IL for Autonomous Driving Policy Learning","created":"2021-01-06","cited_by_count":61,"area":"driving"},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2103.03104","title":"Learning to run a Power Network Challenge: a Retrospective Analysis","created":"2021-03-02","cited_by_count":55,"area":null},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50,"area":null},{"id":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2104.14516","title":"Constructions in combinatorics via neural networks","created":"2021-04-29","cited_by_count":48,"area":null},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44,"area":null},{"id":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43,"area":null},{"id":"2210.05927","title":"Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning","created":"2022-10-12","cited_by_count":43,"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":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2101.11071","title":"The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors","created":"2021-01-26","cited_by_count":41,"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":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"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":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2206.10442","title":"Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning","created":"2022-06-21","cited_by_count":35,"area":"offlinerl"},{"id":"2103.05115","title":"Deep reinforcement learning in medical imaging: A literature review","created":"2021-03-05","cited_by_count":34,"area":null},{"id":"2110.13484","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","created":"2021-10-26","cited_by_count":34,"area":null},{"id":"2106.11365","title":"Distributed Heuristic Multi-Agent Path Finding with Communication","created":"2021-06-21","cited_by_count":32,"area":null},{"id":"2109.05413","title":"Learning Selective Communication for Multi-Agent Path Finding","created":"2021-09-12","cited_by_count":32,"area":"offlinerl"},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32,"area":null},{"id":"2207.07166","title":"K-level Reasoning for Zero-Shot Coordination in Hanabi","created":"2022-07-14","cited_by_count":32,"area":null},{"id":"2102.08159","title":"RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents","created":"2021-02-16","cited_by_count":31,"area":null},{"id":"2102.13045","title":"Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods","created":"2021-02-25","cited_by_count":31,"area":null},{"id":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","cited_by_count":31,"area":null},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2206.07922","title":"Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications","created":"2022-06-16","cited_by_count":30,"area":null},{"id":"2109.02220","title":"GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization","created":"2021-09-06","cited_by_count":29,"area":null},{"id":"2206.00484","title":"DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems","created":"2022-05-30","cited_by_count":29,"area":null},{"id":"2312.05162","title":"A Review of Cooperation in Multi-agent Learning","created":"2023-12-08","cited_by_count":29,"area":null},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28,"area":null},{"id":"2208.01219","title":"Mobility-Aware Cooperative Caching in Vehicular Edge Computing Based on Asynchronous Federated and Deep Reinforcement Learning","created":"2022-08-02","cited_by_count":28,"area":null},{"id":"2102.03483","title":"Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles","created":"2021-02-06","cited_by_count":27,"area":"driving"},{"id":"2102.09225","title":"Continuous Doubly Constrained Batch Reinforcement Learning","created":"2021-02-18","cited_by_count":27,"area":"offlinerl"},{"id":"2104.09122","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","created":"2021-04-19","cited_by_count":27,"area":"moe"},{"id":"2104.13844","title":"A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning","created":"2021-04-28","cited_by_count":26,"area":null},{"id":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26,"area":null},{"id":"2403.09110","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","created":"2024-03-14","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":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2305.17473","title":"A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU","created":"2023-05-27","cited_by_count":25,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2110.15335","title":"Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learning","created":"2021-10-28","cited_by_count":24,"area":null},{"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":"2206.05266","title":"Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?","created":"2022-06-10","cited_by_count":24,"area":null},{"id":"2306.16893","title":"Traceable Group-Wise Self-Optimizing Feature Transformation Learning: A Dual Optimization Perspective","created":"2023-06-29","cited_by_count":24,"area":null},{"id":"2309.01038","title":"Neurosymbolic Reinforcement Learning and Planning: A Survey","created":"2023-09-02","cited_by_count":24,"area":null},{"id":"2102.07247","title":"Reinforcement Learning for IoT Security: A Comprehensive Survey","created":"2021-02-14","cited_by_count":23,"area":null},{"id":"2103.06469","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","created":"2021-03-11","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":"2106.04335","title":"Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization","created":"2021-06-08","cited_by_count":23,"area":null},{"id":"2108.00128","title":"Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control","created":"2021-07-31","cited_by_count":23,"area":null},{"id":"2406.01309","title":"REvolve: Reward Evolution with Large Language Models using Human Feedback","created":"2024-06-03","cited_by_count":23,"area":"alignment"},{"id":"2208.10483","title":"Prioritizing Samples in Reinforcement Learning with Reducible Loss","created":"2022-08-22","cited_by_count":22,"area":null},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2102.13515","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","created":"2021-02-24","cited_by_count":21,"area":null},{"id":"2106.01854","title":"Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning","created":"2021-06-03","cited_by_count":21,"area":null},{"id":"2309.15421","title":"Deep Learning in Deterministic Computational Mechanics","created":"2023-09-27","cited_by_count":21,"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":"2108.11811","title":"When should agents explore?","created":"2021-08-26","cited_by_count":20,"area":null},{"id":"2204.06127","title":"Reinforcement learning on graphs: A survey","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2209.00532","title":"Actor Prioritized Experience Replay","created":"2022-09-01","cited_by_count":20,"area":null},{"id":"2302.10418","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","created":"2023-02-21","cited_by_count":20,"area":null},{"id":"2101.01857","title":"Reinforcement Learning with Latent Flow","created":"2021-01-06","cited_by_count":19,"area":null},{"id":"2101.02034","title":"Deep Reinforcement Learning with Quantum-inspired Experience Replay","created":"2021-01-06","cited_by_count":19,"area":null}],"next_cursor":"100"}