{"total":786,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"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":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400,"area":"wm"},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372,"area":null},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"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":"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":"2211.04486","title":"Active Example Selection for In-Context Learning","created":"2022-11-08","cited_by_count":196,"area":null},{"id":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194,"area":"driving"},{"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":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158,"area":"offlinerl"},{"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":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143,"area":"wm"},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139,"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":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135,"area":null},{"id":"2309.10150","title":"Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions","created":"2023-09-18","cited_by_count":131,"area":"offlinerl"},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"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":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114,"area":"driving"},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112,"area":null},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111,"area":"offlinerl"},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111,"area":"wm"},{"id":"2102.09430","title":"State Entropy Maximization with Random Encoders for Efficient Exploration","created":"2021-02-18","cited_by_count":108,"area":null},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"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":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90,"area":"offlinerl"},{"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":"2111.03788","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","created":"2021-11-06","cited_by_count":84,"area":"offlinerl"},{"id":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79,"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":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73,"area":"offlinerl"},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","cited_by_count":70,"area":"offlinerl"},{"id":"2202.00161","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","created":"2022-02-01","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":"2101.12195","title":"Playable Video Generation","created":"2021-01-28","cited_by_count":64,"area":null},{"id":"2204.02634","title":"Federated Reinforcement Learning with Environment Heterogeneity","created":"2022-04-06","cited_by_count":63,"area":null},{"id":"2111.08575","title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","created":"2021-11-16","cited_by_count":60,"area":"driving"},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58,"area":null},{"id":"2407.01800","title":"Normalization and effective learning rates in reinforcement learning","created":"2024-07-01","cited_by_count":58,"area":"deeprl"},{"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":"1902.04257","title":"Deep Reinforcement Learning from Policy-Dependent Human Feedback","created":"2019-02-12","cited_by_count":56,"area":"alignment"},{"id":"2308.05384","title":"Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization","created":"2023-08-10","cited_by_count":56,"area":"diffusion"},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50,"area":"offlinerl"},{"id":"2111.11032","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","created":"2021-11-22","cited_by_count":49,"area":null},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49,"area":null},{"id":"2209.09893","title":"Deep Generalized Schr\\\"odinger Bridge","created":"2022-09-20","cited_by_count":47,"area":null},{"id":"2403.12014","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","created":"2024-03-18","cited_by_count":46,"area":"agents"},{"id":"2512.01801","title":"GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation","created":"2025-12-01","cited_by_count":45,"area":"vla"},{"id":"2210.02019","title":"Atari-5: Distilling the Arcade Learning Environment down to Five Games","created":"2022-10-05","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":"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":"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":"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":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","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":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41,"area":"agents"},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2202.03983","title":"Provable Reinforcement Learning with a Short-Term Memory","created":"2022-02-08","cited_by_count":40,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"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":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2104.06272","title":"Podracer architectures for scalable Reinforcement Learning","created":"2021-04-13","cited_by_count":38,"area":null},{"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":"2508.02219","title":"CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning","created":"2025-08-04","cited_by_count":37,"area":"vla"},{"id":"1809.02064","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","created":"2018-09-06","cited_by_count":36,"area":"offlinerl"},{"id":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36,"area":null},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","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":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2103.09575","title":"Regularized Behavior Value Estimation","created":"2021-03-17","cited_by_count":32,"area":"offlinerl"},{"id":"2201.12417","title":"Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error","created":"2022-01-28","cited_by_count":32,"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":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","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":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2305.12487","title":"Augmenting Autotelic Agents with Large Language Models","created":"2023-05-21","cited_by_count":30,"area":"agents"},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"area":null},{"id":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2306.15713","title":"Rethinking Closed-loop Training for Autonomous Driving","created":"2023-06-27","cited_by_count":29,"area":"driving"},{"id":"2407.01704","title":"Weight Clipping for Deep Continual and Reinforcement Learning","created":"2024-07-01","cited_by_count":29,"area":"deeprl"},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null}],"next_cursor":"100"}