{"total":126,"rows":[{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327,"area":null},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"area":null},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2307.08689","title":"COLLIE: Systematic Construction of Constrained Text Generation Tasks","created":"2023-07-17","cited_by_count":70,"area":null},{"id":"2301.02555","title":"\"No, to the Right\" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy","created":"2023-01-06","cited_by_count":60,"area":null},{"id":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","cited_by_count":53,"area":null},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49,"area":null},{"id":"2302.04449","title":"Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals","created":"2023-02-09","cited_by_count":45,"area":null},{"id":"2106.02192","title":"Grounding 'Grounding' in NLP","created":"2021-06-04","cited_by_count":44,"area":null},{"id":"2103.05825","title":"ELLA: Exploration through Learned Language Abstraction","created":"2021-03-10","cited_by_count":42,"area":null},{"id":"2204.03972","title":"Contrastive language and vision learning of general fashion concepts","created":"2022-04-08","cited_by_count":42,"area":null},{"id":"2110.02406","title":"Word Acquisition in Neural Language Models","created":"2021-10-05","cited_by_count":41,"area":null},{"id":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39,"area":null},{"id":"2109.10129","title":"Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits","created":"2021-09-21","cited_by_count":38,"area":null},{"id":"2401.14151","title":"True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning","created":"2024-01-25","cited_by_count":36,"area":null},{"id":"2304.09853","title":"Bridging RL Theory and Practice with the Effective Horizon","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"area":null},{"id":"2106.02097","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","created":"2021-06-03","cited_by_count":27,"area":null},{"id":"2111.03205","title":"LILA: Language-Informed Latent Actions","created":"2021-11-05","cited_by_count":27,"area":null},{"id":"2102.07024","title":"Interactive Learning from Activity Description","created":"2021-02-13","cited_by_count":26,"area":null},{"id":"2105.10830","title":"Learning First-Order Representations for Planning from Black-Box States: New Results","created":"2021-05-23","cited_by_count":23,"area":null},{"id":"2206.09674","title":"EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL","created":"2022-06-20","cited_by_count":23,"area":null},{"id":"2205.06002","title":"Learning Generalized Policies Without Supervision Using GNNs","created":"2022-05-12","cited_by_count":22,"area":null},{"id":"2310.08922","title":"LLaMA Rider: Spurring Large Language Models to Explore the Open World","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2402.09844","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","created":"2024-02-15","cited_by_count":21,"area":null},{"id":"2109.08994","title":"ReaSCAN: Compositional Reasoning in Language Grounding","created":"2021-09-18","cited_by_count":19,"area":null},{"id":"2103.09815","title":"TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL","created":"2021-03-17","cited_by_count":18,"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":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2206.15049","title":"ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time","created":"2022-06-30","cited_by_count":16,"area":null},{"id":"2308.03028","title":"Pre-Trained Large Language Models for Industrial Control","created":"2023-08-06","cited_by_count":16,"area":null},{"id":"2109.12243","title":"Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?","created":"2021-09-25","cited_by_count":15,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2106.14321","title":"Draw Me a Flower: Processing and Grounding Abstraction in Natural Language","created":"2021-06-27","cited_by_count":14,"area":null},{"id":"2206.08353","title":"Towards Understanding How Machines Can Learn Causal Overhypotheses","created":"2022-06-16","cited_by_count":14,"area":null},{"id":"2312.08958","title":"LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers","created":"2023-12-14","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":"2211.00247","title":"Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning","created":"2022-11-01","cited_by_count":11,"area":null},{"id":"2402.16354","title":"Language-guided Skill Learning with Temporal Variational Inference","created":"2024-02-26","cited_by_count":11,"area":null},{"id":"2603.15381","title":"Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2205.06111","title":"Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2304.13424","title":"Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories","created":"2023-04-26","cited_by_count":9,"area":null},{"id":"2308.07795","title":"Learning to Identify Critical States for Reinforcement Learning from Videos","created":"2023-08-15","cited_by_count":9,"area":null},{"id":"2311.02171","title":"Emergence of Abstract State Representations in Embodied Sequence Modeling","created":"2023-11-03","cited_by_count":9,"area":null},{"id":"2402.14304","title":"Vision-Language Navigation with Embodied Intelligence: A Survey","created":"2024-02-22","cited_by_count":9,"area":null},{"id":"2211.03352","title":"Curriculum-based Asymmetric Multi-task Reinforcement Learning","created":"2022-11-07","cited_by_count":8,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2310.08702","title":"ELDEN: Exploration via Local Dependencies","created":"2023-10-12","cited_by_count":8,"area":null},{"id":"2405.15194","title":"Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning","created":"2024-05-24","cited_by_count":8,"area":null},{"id":"2503.14576","title":"SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2025-03-18","cited_by_count":8,"area":null},{"id":"2101.00692","title":"Learning General Policies from Small Examples Without Supervision","created":"2021-01-03","cited_by_count":7,"area":null},{"id":"2105.09992","title":"Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness","created":"2021-05-20","cited_by_count":7,"area":null},{"id":"2106.08858","title":"Grounding Spatio-Temporal Language with Transformers","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2107.00956","title":"SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents","created":"2021-07-02","cited_by_count":7,"area":null},{"id":"2108.02846","title":"Communicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scene","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2202.10430","title":"Learning Causal Overhypotheses through Exploration in Children and Computational Models","created":"2022-02-21","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":"2505.22349","title":"ChatPD: An LLM-driven Paper-Dataset Networking System","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2506.06376","title":"Enhancing Decision-Making of Large Language Models via Actor-Critic","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2203.04806","title":"One-Shot Learning from a Demonstration with Hierarchical Latent Language","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2312.06258","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2602.05843","title":"OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2603.13372","title":"The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning","created":"2026-03-09","cited_by_count":6,"area":null},{"id":"2104.08874","title":"Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction","created":"2021-04-18","cited_by_count":5,"area":null},{"id":"2109.03554","title":"Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning","created":"2021-09-08","cited_by_count":5,"area":null},{"id":"2109.07195","title":"Target Languages (vs. Inductive Biases) for Learning to Act and Plan","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2206.03139","title":"Intra-agent speech permits zero-shot task acquisition","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2205.15752","title":"Hierarchies of Reward Machines","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2207.02518","title":"Compositional Generalization in Grounded Language Learning via Induced Model Sparsity","created":"2022-07-06","cited_by_count":4,"area":null},{"id":"2310.00229","title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2312.10289","title":"Active Reinforcement Learning for Robust Building Control","created":"2023-12-16","cited_by_count":4,"area":null},{"id":"2405.04118","title":"Policy Learning with a Language Bottleneck","created":"2024-05-07","cited_by_count":4,"area":null},{"id":"2406.11334","title":"Program Synthesis Benchmark for Visual Programming in XLogoOnline Environment","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2407.03964","title":"Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2504.09763","title":"Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2204.04308","title":"Grounding Hindsight Instructions in Multi-Goal Reinforcement Learning for Robotics","created":"2022-04-08","cited_by_count":3,"area":null},{"id":"2205.13079","title":"Learning to Query Internet Text for Informing Reinforcement Learning Agents","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2510.18407","title":"Heterogeneous Adversarial Play in Interactive Environments","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2108.02095","title":"Human-In-The-Loop Document Layout Analysis","created":"2021-08-04","cited_by_count":2,"area":null},{"id":"2305.12880","title":"Yes, this Way! Learning to Ground Referring Expressions into Actions with Intra-episodic Feedback from Supportive Teachers","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2312.04736","title":"Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2403.17497","title":"Sharing the Cost of Success: A Game for Evaluating and Learning Collaborative Multi-Agent Instruction Giving and Following Policies","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2407.04158","title":"ELCC: the Emergent Language Corpus Collection","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2411.18201","title":"Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2505.11962","title":"CrafText Benchmark: Advancing Instruction Following in Complex Multimodal Open-Ended World","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2602.17497","title":"Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2104.13207","title":"SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents","created":"2021-04-27","cited_by_count":1,"area":null},{"id":"2109.06436","title":"YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker","created":"2021-09-14","cited_by_count":1,"area":null},{"id":"2204.13192","title":"Counterfactual Explanations for Natural Language Interfaces","created":"2022-04-27","cited_by_count":1,"area":null},{"id":"2209.02066","title":"Trust in Language Grounding: a new AI challenge for human-robot teams","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2210.02549","title":"Benchmarking Learning Efficiency in Deep Reservoir Computing","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2211.10168","title":"Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action Corrections","created":"2022-11-18","cited_by_count":1,"area":null},{"id":"2402.04824","title":"Learning Communication Policies for Different Follower Behaviors in a Collaborative Reference Game","created":"2024-02-07","cited_by_count":1,"area":null},{"id":"2402.12061","title":"All Language Models Large and Small","created":"2024-02-19","cited_by_count":1,"area":null}],"next_cursor":"100"}