{"total":89,"rows":[{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2211.04325","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","created":"2022-10-26","cited_by_count":195,"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":"2403.08321","title":"ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation","created":"2024-03-13","cited_by_count":108,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2306.13229","title":"TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning","created":"2023-06-22","cited_by_count":57,"area":null},{"id":"2207.08229","title":"Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models","created":"2022-07-17","cited_by_count":45,"area":null},{"id":"2210.07241","title":"Visual Reinforcement Learning with Self-Supervised 3D Representations","created":"2022-10-13","cited_by_count":45,"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":"2201.12096","title":"Mask-based Latent Reconstruction for Reinforcement Learning","created":"2022-01-28","cited_by_count":39,"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":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2307.03567","title":"SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networks","created":"2023-07-07","cited_by_count":24,"area":null},{"id":"2307.10710","title":"Reparameterized Policy Learning for Multimodal Trajectory Optimization","created":"2023-07-20","cited_by_count":20,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2306.13840","title":"Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2507.08800","title":"NeuralOS: Towards Simulating Operating Systems via Neural Generative Models","created":"2025-07-11","cited_by_count":19,"area":null},{"id":"2204.10817","title":"Reward Reports for Reinforcement Learning","created":"2022-04-22","cited_by_count":18,"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":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2503.18871","title":"Bootstrapped Model Predictive Control","created":"2025-03-24","cited_by_count":16,"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":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15,"area":null},{"id":"2210.10763","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","created":"2022-10-19","cited_by_count":15,"area":null},{"id":"2310.11305","title":"MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2203.08222","title":"Zipfian environments for Reinforcement Learning","created":"2022-03-15","cited_by_count":13,"area":null},{"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":"2312.15908","title":"Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding","created":"2023-12-26","cited_by_count":12,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2203.16707","title":"Monte Carlo Tree Search based Hybrid Optimization of Variational Quantum Circuits","created":"2022-03-30","cited_by_count":10,"area":null},{"id":"2208.01545","title":"The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence","created":"2022-08-02","cited_by_count":10,"area":null},{"id":"2307.13453","title":"Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results","created":"2023-07-25","cited_by_count":9,"area":null},{"id":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2210.10913","title":"Palm up: Playing in the Latent Manifold for Unsupervised Pretraining","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","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":"2306.02006","title":"MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning","created":"2023-06-03","cited_by_count":6,"area":null},{"id":"2306.13841","title":"Is Pre-training Truly Better Than Meta-Learning?","created":"2023-06-24","cited_by_count":6,"area":null},{"id":"2406.00614","title":"Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction","created":"2024-06-02","cited_by_count":6,"area":null},{"id":"2211.13337","title":"Multi-Environment Pretraining Enables Transfer to Action Limited Datasets","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2302.04009","title":"Investigating the role of model-based learning in exploration and transfer","created":"2023-02-08","cited_by_count":5,"area":null},{"id":"2510.08962","title":"Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2511.06142","title":"MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning","created":"2025-11-08","cited_by_count":5,"area":null},{"id":"2605.00751","title":"NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2210.01426","title":"Continuous Monte Carlo Graph Search","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2210.12628","title":"Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions","created":"2022-10-23","cited_by_count":4,"area":null},{"id":"2505.15293","title":"LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2208.11535","title":"A model-based approach to meta-Reinforcement Learning: Transformers and tree search","created":"2022-08-24","cited_by_count":3,"area":null},{"id":"2211.14939","title":"Applying Deep Reinforcement Learning to the HP Model for Protein Structure Prediction","created":"2022-11-27","cited_by_count":3,"area":null},{"id":"2308.09289","title":"Preference-conditioned Pixel-based AI Agent For Game Testing","created":"2023-08-18","cited_by_count":3,"area":null},{"id":"2310.06513","title":"Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction","created":"2023-10-10","cited_by_count":3,"area":null},{"id":"2512.00672","title":"ML-Tool-Bench: Tool-Augmented Planning for ML Tasks","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2205.10044","title":"Towards biologically plausible Dreaming and Planning in recurrent spiking networks","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2210.09366","title":"Bridging the Gap between Artificial Intelligence and Artificial General Intelligence: A Ten Commandment Framework for Human-Like Intelligence","created":"2022-10-17","cited_by_count":2,"area":null},{"id":"2211.13260","title":"Actively Learning Costly Reward Functions for Reinforcement Learning","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2303.05205","title":"Real-time scheduling of renewable power systems through planning-based reinforcement learning","created":"2023-03-09","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":"2404.05440","title":"Tree Search-Based Policy Optimization under Stochastic Execution Delay","created":"2024-04-08","cited_by_count":2,"area":null},{"id":"2404.16364","title":"ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2501.12216","title":"RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2210.00828","title":"Mastering Spatial Graph Prediction of Road Networks","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2304.10500","title":"Transformer Models for Type Inference in the Simply Typed Lambda Calculus: A Case Study in Deep Learning for Code","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2306.17366","title":"$\\lambda$-models: Effective Decision-Aware Reinforcement Learning with Latent Models","created":"2023-06-30","cited_by_count":1,"area":null},{"id":"2409.15753","title":"Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2411.04580","title":"Demystifying MuZero Planning: Interpreting the Learned Model","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2509.06714","title":"RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2601.22662","title":"Task-Aware LLM Council with Adaptive Decision Pathways for Decision Support","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2112.13121","title":"The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence","created":"2021-12-24","cited_by_count":0,"area":null},{"id":"2204.03525","title":"Temporal Alignment for History Representation in Reinforcement Learning","created":"2022-04-07","cited_by_count":0,"area":null},{"id":"2208.09094","title":"Towards Situation Awareness and Attention Guidance in a Multiplayer Environment using Augmented Reality and Carcassonne","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2302.06009","title":"Policy-Induced Self-Supervision Improves Representation Finetuning in Visual RL","created":"2023-02-12","cited_by_count":0,"area":null},{"id":"2304.07219","title":"Model Predictive Control with Self-supervised Representation Learning","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2304.13223","title":"Reinforcement Learning with Partial Parametric Model Knowledge","created":"2023-04-26","cited_by_count":0,"area":null},{"id":"2306.03408","title":"Agents Explore the Environment Beyond Good Actions to Improve Their Model for Better Decisions","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2308.08693","title":"AI planning in the imagination: High-level planning on learned abstract search spaces","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2310.14009","title":"One is More: Diverse Perspectives within a Single Network for Efficient DRL","created":"2023-10-21","cited_by_count":0,"area":null},{"id":"2407.03210","title":"Combining AI Control Systems and Human Decision Support via Robustness and Criticality","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2409.11600","title":"No Saved Kaleidosope: an 100% Jitted Neural Network Coding Language with Pythonic Syntax","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2410.17428","title":"Uncovering RL Integration in SSL Loss: Objective-Specific Implications for Data-Efficient RL","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2412.06940","title":"Digital Twin-Empowered Voltage Control for Power Systems","created":"2024-12-09","cited_by_count":0,"area":null},{"id":"2504.14636","title":"When Search Teaches Style: Causal Internalization of Tactical Priors in AlphaZero","created":"2025-04-20","cited_by_count":0,"area":null},{"id":"2603.07437","title":"Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2606.15301","title":"Discovering Lattice Reduction Strategies via Self-Play","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.26946","title":"Belief-Guided Decision Making with Uncertainty Gating in the Game of Go","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.36932","title":"Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}