{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"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":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"2502.19417","title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","created":"2025-02-26","cited_by_count":221},{"id":"1611.01796","title":"Modular Multitask Reinforcement Learning with Policy Sketches","created":"2016-11-06","cited_by_count":203},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203},{"id":"2010.03950","title":"Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning","created":"2020-10-06","cited_by_count":191},{"id":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188},{"id":"2310.12921","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","created":"2023-10-19","cited_by_count":165},{"id":"2301.03728","title":"Scaling Laws for Generative Mixed-Modal Language Models","created":"2023-01-10","cited_by_count":134},{"id":"1612.03471","title":"Reinforcement Learning With Temporal Logic Rewards","created":"2016-12-11","cited_by_count":117},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112},{"id":"2405.04776","title":"Chain of Thoughtlessness? An Analysis of CoT in Planning","created":"2024-05-08","cited_by_count":103},{"id":"1706.06551","title":"Grounded Language Learning in a Simulated 3D World","created":"2017-06-20","cited_by_count":100},{"id":"1706.05064","title":"Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning","created":"2017-06-15","cited_by_count":98},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97},{"id":"1806.01946","title":"Learning to Understand Goal Specifications by Modelling Reward","created":"2018-06-05","cited_by_count":80},{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74},{"id":"1706.07230","title":"Gated-Attention Architectures for Task-Oriented Language Grounding","created":"2017-06-22","cited_by_count":72},{"id":"2008.09293","title":"A Composable Specification Language for Reinforcement Learning Tasks","created":"2020-08-21","cited_by_count":69},{"id":"1609.07409","title":"Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications","created":"2016-09-23","cited_by_count":67},{"id":"2312.09187","title":"Vision-Language Models as a Source of Rewards","created":"2023-12-14","cited_by_count":66},{"id":"2305.07766","title":"NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models","created":"2023-05-12","cited_by_count":59},{"id":"2009.01719","title":"Grounded Language Learning Fast and Slow","created":"2020-09-03","cited_by_count":54},{"id":"2302.11649","title":"Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments","created":"2023-02-22","cited_by_count":53},{"id":"2001.01394","title":"A Boolean Task Algebra for Reinforcement Learning","created":"2020-01-06","cited_by_count":48},{"id":"2006.01110","title":"Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas","created":"2020-06-01","cited_by_count":36},{"id":"2007.01498","title":"Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks","created":"2020-07-03","cited_by_count":28},{"id":"2009.03855","title":"Induction and Exploitation of Subgoal Automata for Reinforcement Learning","created":"2020-09-08","cited_by_count":26},{"id":"2406.00645","title":"FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning","created":"2024-06-02","cited_by_count":26},{"id":"2410.04631","title":"DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL","created":"2024-10-06","cited_by_count":21},{"id":"2303.02135","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","created":"2023-03-03","cited_by_count":19},{"id":"2411.00205","title":"Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning","created":"2024-10-31","cited_by_count":19},{"id":"2110.09461","title":"In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications","created":"2021-10-18","cited_by_count":17},{"id":"1901.02077","title":"Specification Patterns for Robotic Missions","created":"2019-01-07","cited_by_count":16},{"id":"2406.00120","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","created":"2024-05-31","cited_by_count":11},{"id":"2211.10902","title":"Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines","created":"2022-11-20","cited_by_count":10},{"id":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9},{"id":"2408.08677","title":"Neural Reward Machines","created":"2024-08-16","cited_by_count":7},{"id":"2408.14871","title":"Learning Robust Reward Machines from Noisy Labels","created":"2024-08-27","cited_by_count":7},{"id":"2401.11325","title":"Detecting Hidden Triggers: Mapping Non-Markov Reward Functions to Markov","created":"2024-01-20","cited_by_count":5},{"id":"2301.02952","title":"Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior","created":"2023-01-08","cited_by_count":4},{"id":"2306.08400","title":"Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning","created":"2023-06-14","cited_by_count":3}],"next_cursor":null}