{"total":122,"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":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200,"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":"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":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143,"area":null},{"id":"2104.00405","title":"Avalanche: an End-to-End Library for Continual Learning","created":"2021-04-01","cited_by_count":124,"area":null},{"id":"2210.07105","title":"CORL: Research-oriented Deep Offline Reinforcement Learning Library","created":"2022-10-13","cited_by_count":119,"area":"offlinerl"},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111,"area":"offlinerl"},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"area":null},{"id":"2111.03788","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","created":"2021-11-06","cited_by_count":84,"area":"offlinerl"},{"id":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78,"area":"moe"},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"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":"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":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2111.09395","title":"FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance","created":"2021-11-07","cited_by_count":58,"area":null},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50,"area":"offlinerl"},{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"area":null},{"id":"2412.08442","title":"From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons","created":"2024-12-11","cited_by_count":42,"area":"mllm"},{"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":"2109.11052","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","created":"2021-09-22","cited_by_count":37,"area":null},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2105.12272","title":"Provable Representation Learning for Imitation with Contrastive Fourier Features","created":"2021-05-26","cited_by_count":34,"area":"offlinerl"},{"id":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2203.00543","title":"On the Generalization of Representations in Reinforcement Learning","created":"2022-03-01","cited_by_count":28,"area":null},{"id":"2306.03186","title":"Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2310.07418","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","created":"2023-10-11","cited_by_count":28,"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":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25,"area":null},{"id":"2110.13578","title":"Distributional Reinforcement Learning for Multi-Dimensional Reward Functions","created":"2021-10-26","cited_by_count":22,"area":null},{"id":"2103.08057","title":"RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems","created":"2021-03-14","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":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2101.00135","title":"Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approach","created":"2021-01-01","cited_by_count":18,"area":null},{"id":"2110.14118","title":"Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning","created":"2021-10-27","cited_by_count":17,"area":"offlinerl"},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2105.06696","title":"Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning","created":"2021-05-14","cited_by_count":15,"area":null},{"id":"2109.00525","title":"Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation","created":"2021-09-01","cited_by_count":15,"area":"distill"},{"id":"2102.12769","title":"No-Regret Reinforcement Learning with Heavy-Tailed Rewards","created":"2021-02-25","cited_by_count":14,"area":null},{"id":"2110.01528","title":"Large Batch Experience Replay","created":"2021-10-04","cited_by_count":14,"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":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2211.01052","title":"Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints","created":"2022-11-02","cited_by_count":13,"area":"offlinerl"},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2305.13681","title":"GUARD: A Safe Reinforcement Learning Benchmark","created":"2023-05-23","cited_by_count":13,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2412.17113","title":"Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps","created":"2024-12-22","cited_by_count":11,"area":"deeprl"},{"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":"2104.08441","title":"Action Advising with Advice Imitation in Deep Reinforcement Learning","created":"2021-04-17","cited_by_count":10,"area":"distill"},{"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":"2202.11818","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","created":"2022-02-23","cited_by_count":10,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2112.05923","title":"ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning","created":"2021-12-11","cited_by_count":9,"area":null},{"id":"2310.13396","title":"RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup","created":"2023-10-20","cited_by_count":8,"area":null},{"id":"2112.05848","title":"Faster Deep Reinforcement Learning with Slower Online Network","created":"2021-12-10","cited_by_count":7,"area":null},{"id":"2203.08542","title":"Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","created":"2024-11-06","cited_by_count":7,"area":"deeprl"},{"id":"2403.02107","title":"Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning","created":"2024-03-04","cited_by_count":6,"area":"deeprl"},{"id":"2405.04342","title":"The Curse of Diversity in Ensemble-Based Exploration","created":"2024-05-07","cited_by_count":6,"area":"deeprl"},{"id":"2503.01437","title":"Eau De $Q$-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning","created":"2025-03-03","cited_by_count":6,"area":"deeprl"},{"id":"2112.04123","title":"ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"id":"2308.00707","title":"Approximate Model-Based Shielding for Safe Reinforcement Learning","created":"2023-07-27","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2312.16248","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2410.23810","title":"CALE: Continuous Arcade Learning Environment","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2109.14419","title":"On the Estimation Bias in Double Q-Learning","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2203.07171","title":"Orchestrated Value Mapping for Reinforcement Learning","created":"2022-03-14","cited_by_count":4,"area":null},{"id":"2209.10055","title":"Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games","created":"2022-09-21","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":"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":"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":"2506.04398","title":"Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2102.06808","title":"Planning and Learning Using Adaptive Entropy Tree Search","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2110.00950","title":"An Unsupervised Video Game Playstyle Metric via State Discretization","created":"2021-10-03","cited_by_count":3,"area":null},{"id":"2208.12136","title":"A Comparison of Reinforcement Learning Frameworks for Software Testing Tasks","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2310.16546","title":"Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2310.19804","title":"A Kernel Perspective on Behavioural Metrics for Markov Decision Processes","created":"2023-10-05","cited_by_count":3,"area":null},{"id":"2405.16195","title":"Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning","created":"2024-05-25","cited_by_count":3,"area":"deeprl"},{"id":"2504.04911","title":"IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR","created":"2025-04-07","cited_by_count":3,"area":null},{"id":"2510.16175","title":"The Formalism-Implementation Gap in Reinforcement Learning Research","created":"2025-10-17","cited_by_count":3,"area":"deeprl"},{"id":"2603.06413","title":"A Reference Architecture of Reinforcement Learning Frameworks","created":"2026-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2112.07424","title":"Conjugated Discrete Distributions for Distributional Reinforcement Learning","created":"2021-12-14","cited_by_count":2,"area":null},{"id":"2312.11414","title":"The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2404.17687","title":"Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Review","created":"2024-04-26","cited_by_count":2,"area":"deeprl"},{"id":"2408.06051","title":"Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in Games","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2510.02590","title":"Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning","created":"2025-10-02","cited_by_count":2,"area":"deeprl"},{"id":"2104.10995","title":"A learning gap between neuroscience and reinforcement learning","created":"2021-04-22","cited_by_count":1,"area":null},{"id":"2206.06485","title":"What Should I Know? Using Meta-gradient Descent for Predictive Feature Discovery in a Single Stream of Experience","created":"2022-06-13","cited_by_count":1,"area":null}],"next_cursor":"100"}