{"total":163,"rows":[{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2110.13309","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","created":"2021-10-25","cited_by_count":271,"area":null},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162,"area":null},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156,"area":null},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"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":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2110.07732","title":"The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization","created":"2021-10-14","cited_by_count":62,"area":null},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62,"area":null},{"id":"2111.02329","title":"Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods","created":"2021-11-03","cited_by_count":61,"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":"2103.00776","title":"Single-Shot Motion Completion with Transformer","created":"2021-03-01","cited_by_count":59,"area":null},{"id":"2109.07152","title":"Incorporating Residual and Normalization Layers into Analysis of Masked Language Models","created":"2021-09-15","cited_by_count":51,"area":null},{"id":"2108.01210","title":"Representation learning for neural population activity with Neural Data Transformers","created":"2021-08-02","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":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46,"area":null},{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2210.13383","title":"Evaluating Long-Term Memory in 3D Mazes","created":"2022-10-24","cited_by_count":43,"area":null},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42,"area":null},{"id":"2206.06614","title":"Transformers are Meta-Reinforcement Learners","created":"2022-06-14","cited_by_count":41,"area":null},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","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":"2105.14039","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","created":"2021-05-28","cited_by_count":40,"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":"2102.02926","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","created":"2021-02-04","cited_by_count":36,"area":null},{"id":"2112.03753","title":"Tell me why! Explanations support learning relational and causal structure","created":"2021-12-07","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":"2104.01655","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","created":"2021-04-04","cited_by_count":35,"area":null},{"id":"2105.06548","title":"Not All Memories are Created Equal: Learning to Forget by Expiring","created":"2021-05-13","cited_by_count":32,"area":null},{"id":"2305.15930","title":"End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes","created":"2023-05-25","cited_by_count":32,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","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":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"area":null},{"id":"2211.10869","title":"UniMASK: Unified Inference in Sequential Decision Problems","created":"2022-11-20","cited_by_count":24,"area":null},{"id":"2107.05944","title":"The Piano Inpainting Application","created":"2021-07-13","cited_by_count":23,"area":null},{"id":"2201.12569","title":"Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes","created":"2022-01-29","cited_by_count":23,"area":null},{"id":"2106.05856","title":"MolGrow: A Graph Normalizing Flow for Hierarchical Molecular Generation","created":"2021-02-03","cited_by_count":22,"area":null},{"id":"2107.05431","title":"CoBERL: Contrastive BERT for Reinforcement Learning","created":"2021-07-12","cited_by_count":21,"area":null},{"id":"2107.08408","title":"Pre-trained Language Models as Prior Knowledge for Playing Text-based Games","created":"2021-07-18","cited_by_count":21,"area":null},{"id":"2107.08170","title":"Megaverse: Simulating Embodied Agents at One Million Experiences per Second","created":"2021-07-17","cited_by_count":20,"area":null},{"id":"2203.11889","title":"Insights From the NeurIPS 2021 NetHack Challenge","created":"2022-03-22","cited_by_count":20,"area":null},{"id":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2305.19044","title":"Exploring the Promise and Limits of Real-Time Recurrent Learning","created":"2023-05-30","cited_by_count":19,"area":null},{"id":"2410.14250","title":"Vision-Language Navigation with Energy-Based Policy","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2110.15949","title":"Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains","created":"2021-10-29","cited_by_count":18,"area":null},{"id":"2310.02902","title":"Searching for High-Value Molecules Using Reinforcement Learning and Transformers","created":"2023-10-04","cited_by_count":18,"area":null},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2411.10830","title":"One-Layer Transformer Provably Learns One-Nearest Neighbor In Context","created":"2024-11-16","cited_by_count":16,"area":null},{"id":"2509.09498","title":"SEDM: Selective Self-Evolving Distributed Memory for Agents","created":"2025-09-11","cited_by_count":16,"area":null},{"id":"2105.08086","title":"Neural Error Mitigation of Near-Term Quantum Simulations","created":"2021-05-17","cited_by_count":15,"area":null},{"id":"2509.16189","title":"Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences","created":"2025-09-19","cited_by_count":15,"area":null},{"id":"2107.01366","title":"Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN","created":"2021-07-03","cited_by_count":14,"area":null},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2604.18933","title":"Gated Memory Policy: In-Context Memorization and Adaptation","created":"2026-04-21","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":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2307.08082","title":"POMDP inference and robust solution via deep reinforcement learning: An application to railway optimal maintenance","created":"2023-07-16","cited_by_count":13,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2203.07413","title":"Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning","created":"2022-03-14","cited_by_count":11,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2202.11818","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","created":"2022-02-23","cited_by_count":10,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2303.05197","title":"Mastering Strategy Card Game (Hearthstone) with Improved Techniques","created":"2023-03-09","cited_by_count":10,"area":null},{"id":"2410.01706","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2203.13375","title":"Deep reinforcement learning for optimal well control in subsurface systems with uncertain geology","created":"2022-03-24","cited_by_count":9,"area":null},{"id":"2301.05334","title":"TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems","created":"2023-01-13","cited_by_count":9,"area":null},{"id":"2303.08789","title":"PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining","created":"2023-03-15","cited_by_count":9,"area":null},{"id":"2310.04128","title":"Reinforcement Learning with Fast and Forgetful Memory","created":"2023-10-06","cited_by_count":9,"area":null},{"id":"2111.03474","title":"Supervised Advantage Actor-Critic for Recommender Systems","created":"2021-11-05","cited_by_count":8,"area":null},{"id":"2303.16189","title":"Planning with Sequence Models through Iterative Energy Minimization","created":"2023-03-28","cited_by_count":8,"area":null},{"id":"2306.12554","title":"Improving Long-Horizon Imitation Through Instruction Prediction","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2403.05318","title":"Looking Ahead to Avoid Being Late: Solving Hard-Constrained Traveling Salesman Problem","created":"2024-03-08","cited_by_count":8,"area":null},{"id":"2410.01265","title":"Transformers Handle Endogeneity in In-Context Linear Regression","created":"2024-10-02","cited_by_count":8,"area":null},{"id":"2106.02613","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2301.12305","title":"Composing Task Knowledge with Modular Successor Feature Approximators","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2403.07559","title":"Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2406.14662","title":"Advantage Alignment Algorithms","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2204.13326","title":"Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers","created":"2022-04-28","cited_by_count":6,"area":null},{"id":"2211.06407","title":"Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2212.14538","title":"Transformer in Transformer as Backbone for Deep Reinforcement Learning","created":"2022-12-30","cited_by_count":6,"area":null},{"id":"2310.15719","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2505.06584","title":"JAEGER: Dual-Level Humanoid Whole-Body Controller","created":"2025-05-10","cited_by_count":6,"area":null},{"id":"2509.23186","title":"Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2510.07151","title":"ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2101.11836","title":"DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting","created":"2021-01-28","cited_by_count":5,"area":null},{"id":"2204.13906","title":"Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery","created":"2022-04-29","cited_by_count":5,"area":null},{"id":"2206.03721","title":"Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer","created":"2022-06-08","cited_by_count":5,"area":null}],"next_cursor":"100"}