{"list":"other","total":90,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2404.11018","title":"Many-Shot In-Context Learning","created":"2024-04-17","cited_by_count":206},{"id":"2207.06881","title":"Recurrent Memory Transformer","created":"2022-07-14","cited_by_count":203},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190},{"id":"1806.07857","title":"RUDDER: Return Decomposition for Delayed Rewards","created":"2018-06-20","cited_by_count":173},{"id":"1703.01988","title":"Neural Episodic Control","created":"2017-03-06","cited_by_count":151},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"1912.02875","title":"Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions","created":"2019-12-05","cited_by_count":125},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110},{"id":"2212.04458","title":"General-Purpose In-Context Learning by Meta-Learning Transformers","created":"2022-12-08","cited_by_count":105},{"id":"1606.04460","title":"Model-Free Episodic Control","created":"2016-06-14","cited_by_count":102},{"id":"1909.00025","title":"Meta-Learning with Warped Gradient Descent","created":"2019-08-30","cited_by_count":98},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"2310.08566","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","created":"2023-10-12","cited_by_count":83},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71},{"id":"1905.03030","title":"Meta-learning of Sequential Strategies","created":"2019-05-08","cited_by_count":70},{"id":"1910.04098","title":"Improving Generalization in Meta Reinforcement Learning using Learned Objectives","created":"2019-10-09","cited_by_count":68},{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63},{"id":"2110.10819","title":"Shaking the foundations: delusions in sequence models for interaction and control","created":"2021-10-20","cited_by_count":62},{"id":"1803.10760","title":"Unsupervised Predictive Memory in a Goal-Directed Agent","created":"2018-03-28","cited_by_count":55},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55},{"id":"2009.01719","title":"Grounded Language Learning Fast and Slow","created":"2020-09-03","cited_by_count":54},{"id":"2210.13383","title":"Evaluating Long-Term Memory in 3D Mazes","created":"2022-10-24","cited_by_count":43},{"id":"2206.06614","title":"Transformers are Meta-Reinforcement Learners","created":"2022-06-14","cited_by_count":41},{"id":"2302.04858","title":"Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning","created":"2023-02-09","cited_by_count":41},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39},{"id":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39},{"id":"2009.14108","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","created":"2020-09-29","cited_by_count":36},{"id":"1802.10542","title":"Memory-based Parameter Adaptation","created":"2018-02-28","cited_by_count":35},{"id":"2305.16554","title":"Emergent Agentic Transformer from Chain of Hindsight Experience","created":"2023-05-26","cited_by_count":33},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28},{"id":"2111.04714","title":"A Dataset Perspective on Offline Reinforcement Learning","created":"2021-11-08","cited_by_count":27},{"id":"2312.12275","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","created":"2023-12-19","cited_by_count":27},{"id":"2405.20692","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","created":"2024-05-31","cited_by_count":26},{"id":"2206.05314","title":"Large-Scale Retrieval for Reinforcement Learning","created":"2022-06-10","cited_by_count":24},{"id":"2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","created":"2023-12-20","cited_by_count":24},{"id":"2406.08973","title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","created":"2024-06-13","cited_by_count":14},{"id":"1505.00521","title":"Reinforcement Learning Neural Turing Machines - Revised","created":"2015-05-04","cited_by_count":11},{"id":"2111.10247","title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","created":"2021-11-19","cited_by_count":10},{"id":"2402.06402","title":"Hierarchical Transformers are Efficient Meta-Reinforcement Learners","created":"2024-02-09","cited_by_count":8}],"next_cursor":null}