{"total":807,"rows":[{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045,"area":null},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571,"area":"alignment"},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397,"area":"wm"},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300,"area":"wm"},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248,"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":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"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":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174,"area":null},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173,"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":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146,"area":"wm"},{"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":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"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":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126,"area":"offlinerl"},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"2306.03831","title":"GEO-Bench: Toward Foundation Models for Earth Monitoring","created":"2023-06-06","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":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114,"area":null},{"id":"2410.18164","title":"TabDPT: Scaling Tabular Foundation Models on Real Data","created":"2024-10-23","cited_by_count":113,"area":null},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108,"area":null},{"id":"2405.16158","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","created":"2024-05-25","cited_by_count":108,"area":"deeprl"},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103,"area":"offlinerl"},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","created":"2025-10-15","cited_by_count":101,"area":null},{"id":"2202.08450","title":"Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization","created":"2022-02-17","cited_by_count":97,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2510.11977","title":"Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation","created":"2025-10-13","cited_by_count":92,"area":"agents"},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89,"area":"offlinerl"},{"id":"2310.10021","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","created":"2023-10-16","cited_by_count":86,"area":"synth"},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78,"area":"moe"},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77,"area":"offlinerl"},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"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":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"area":"alignment"},{"id":"2202.00161","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","created":"2022-02-01","cited_by_count":68,"area":null},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66,"area":"offlinerl"},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"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":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2406.05207","title":"Retrieval & Fine-Tuning for In-Context Tabular Models","created":"2024-06-07","cited_by_count":59,"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":"2502.02316","title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning","created":"2025-02-04","cited_by_count":58,"area":"diffusion"},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"area":null},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54,"area":"wm"},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2110.04135","title":"Revisiting Design Choices in Offline Model-Based Reinforcement Learning","created":"2021-10-08","cited_by_count":50,"area":"offlinerl"},{"id":"2403.00514","title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","created":"2024-03-01","cited_by_count":50,"area":"deeprl"},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49,"area":null},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2305.18499","title":"Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning","created":"2023-05-29","cited_by_count":45,"area":"wm"},{"id":"2505.11289","title":"Meta-World+: An Improved, Standardized, RL Benchmark","created":"2025-05-16","cited_by_count":43,"area":"deeprl"},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42,"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":"2310.13595","title":"The History and Risks of Reinforcement Learning and Human Feedback","created":"2023-10-20","cited_by_count":42,"area":"alignment"},{"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":"2201.12096","title":"Mask-based Latent Reconstruction for Reinforcement Learning","created":"2022-01-28","cited_by_count":39,"area":null},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","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":"2403.04253","title":"Mastering Memory Tasks with World Models","created":"2024-03-07","cited_by_count":38,"area":"wm"},{"id":"2303.14623","title":"Inverse Reinforcement Learning without Reinforcement Learning","created":"2023-03-26","cited_by_count":36,"area":"offlinerl"},{"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":"2504.17838","title":"CaRL: Learning Scalable Planning Policies with Simple Rewards","created":"2025-04-24","cited_by_count":35,"area":"deeprl"},{"id":"2312.08533","title":"World Models via Policy-Guided Trajectory Diffusion","created":"2023-12-13","cited_by_count":34,"area":"wm"},{"id":"2312.01472","title":"BenchMARL: Benchmarking Multi-Agent Reinforcement Learning","created":"2023-12-03","cited_by_count":33,"area":null},{"id":"2406.19320","title":"Efficient World Models with Context-Aware Tokenization","created":"2024-06-27","cited_by_count":33,"area":"wm"},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"id":"2211.11349","title":"Data-Driven Offline Decision-Making via Invariant Representation Learning","created":"2022-11-21","cited_by_count":31,"area":null},{"id":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","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":"2212.11498","title":"Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers","created":"2022-12-22","cited_by_count":30,"area":null},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2210.07573","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","created":"2022-10-14","cited_by_count":29,"area":null},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28,"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":"2204.06815","title":"deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2210.06518","title":"Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories","created":"2022-10-12","cited_by_count":28,"area":"offlinerl"},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"}],"next_cursor":"100"}