{"total":203,"rows":[{"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,"area":null},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750,"area":null},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174,"area":null},{"id":"2303.16755","title":"Training Language Models with Language Feedback at Scale","created":"2023-03-28","cited_by_count":128,"area":"alignment"},{"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":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"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":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2410.05273","title":"HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers","created":"2024-09-12","cited_by_count":75,"area":"mllm"},{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68,"area":null},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67,"area":null},{"id":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59,"area":null},{"id":"2207.05006","title":"TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs","created":"2022-07-11","cited_by_count":59,"area":null},{"id":"2204.14146","title":"Training Language Models with Language Feedback","created":"2022-04-29","cited_by_count":49,"area":"alignment"},{"id":"2111.07999","title":"Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization","created":"2021-11-15","cited_by_count":46,"area":null},{"id":"2210.11653","title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning","created":"2022-10-21","cited_by_count":46,"area":null},{"id":"2101.07393","title":"Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning","created":"2021-01-19","cited_by_count":45,"area":null},{"id":"2103.05825","title":"ELLA: Exploration through Learned Language Abstraction","created":"2021-03-10","cited_by_count":42,"area":null},{"id":"2403.02709","title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","created":"2024-03-05","cited_by_count":41,"area":"offlinerl"},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2312.08566","title":"Learning adaptive planning representations with natural language guidance","created":"2023-12-13","cited_by_count":36,"area":null},{"id":"2209.13900","title":"Disentangling Transfer in Continual Reinforcement Learning","created":"2022-09-28","cited_by_count":33,"area":null},{"id":"2305.02412","title":"Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents","created":"2023-05-03","cited_by_count":32,"area":"agents"},{"id":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31,"area":"deeprl"},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2102.12571","title":"The Logical Options Framework","created":"2021-02-24","cited_by_count":25,"area":null},{"id":"2110.06972","title":"Block Contextual MDPs for Continual Learning","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2201.00042","title":"Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments","created":"2021-12-31","cited_by_count":25,"area":null},{"id":"2111.08960","title":"Compositional Transformers for Scene Generation","created":"2021-11-17","cited_by_count":24,"area":null},{"id":"2306.11886","title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","created":"2023-06-20","cited_by_count":24,"area":null},{"id":"2412.08542","title":"MaestroMotif: Skill Design from Artificial Intelligence Feedback","created":"2024-12-11","cited_by_count":24,"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":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22,"area":null},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2410.04631","title":"DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL","created":"2024-10-06","cited_by_count":21,"area":"deeprl"},{"id":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19,"area":null},{"id":"2411.00205","title":"Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning","created":"2024-10-31","cited_by_count":19,"area":"deeprl"},{"id":"2305.01381","title":"Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees","created":"2023-05-02","cited_by_count":18,"area":null},{"id":"2107.03961","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","created":"2021-07-08","cited_by_count":17,"area":null},{"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,"area":null},{"id":"2210.04476","title":"Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks","created":"2022-10-10","cited_by_count":17,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2103.10972","title":"Learning Task Decomposition with Ordered Memory Policy Network","created":"2021-03-19","cited_by_count":15,"area":null},{"id":"2207.02442","title":"Transformers are Adaptable Task Planners","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2305.12633","title":"Multi-task Hierarchical Adversarial Inverse Reinforcement Learning","created":"2023-05-22","cited_by_count":15,"area":"offlinerl"},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2302.08672","title":"Multimodal Subtask Graph Generation from Instructional Videos","created":"2023-02-17","cited_by_count":13,"area":null},{"id":"2406.17768","title":"EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data","created":"2024-06-25","cited_by_count":13,"area":"deeprl"},{"id":"2204.11833","title":"Joint Learning of Reward Machines and Policies in Environments with Partially Known Semantics","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2109.09968","title":"Generalization in Text-based Games via Hierarchical Reinforcement Learning","created":"2021-09-21","cited_by_count":11,"area":null},{"id":"2110.10661","title":"SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark","created":"2021-10-20","cited_by_count":11,"area":null},{"id":"2112.02252","title":"Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction","created":"2021-12-04","cited_by_count":11,"area":null},{"id":"2202.08806","title":"Grammar-Based Grounded Lexicon Learning","created":"2022-02-17","cited_by_count":11,"area":null},{"id":"2209.10341","title":"LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning","created":"2022-09-21","cited_by_count":11,"area":null},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2307.06565","title":"Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification","created":"2023-07-13","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":"2403.17124","title":"Grounding Language Plans in Demonstrations Through Counterfactual Perturbations","created":"2024-03-25","cited_by_count":11,"area":"lr"},{"id":"2406.00120","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","created":"2024-05-31","cited_by_count":11,"area":"deeprl"},{"id":"2507.02424","title":"CyberRAG: An Agentic RAG cyber attack classification and reporting tool","created":"2025-07-03","cited_by_count":11,"area":"rag"},{"id":"2204.09597","title":"Perceiving the World: Question-guided Reinforcement Learning for Text-based Games","created":"2022-03-20","cited_by_count":10,"area":null},{"id":"2208.11445","title":"Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2211.10902","title":"Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines","created":"2022-11-20","cited_by_count":10,"area":null},{"id":"2311.01075","title":"Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2203.04857","title":"Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference","created":"2022-03-09","cited_by_count":9,"area":null},{"id":"2206.03318","title":"LegoNN: Building Modular Encoder-Decoder Models","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2307.16503","title":"Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot","created":"2023-07-31","cited_by_count":9,"area":null},{"id":"2311.05596","title":"LLM Augmented Hierarchical Agents","created":"2023-11-09","cited_by_count":9,"area":"agents"},{"id":"2410.18416","title":"SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2102.11137","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","created":"2021-02-22","cited_by_count":8,"area":null},{"id":"2104.07219","title":"Multitasking Inhibits Semantic Drift","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2306.06253","title":"Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models","created":"2023-06-09","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":"2310.08702","title":"ELDEN: Exploration via Local Dependencies","created":"2023-10-12","cited_by_count":8,"area":null},{"id":"1812.01483","title":"CompILE: Compositional Imitation Learning and Execution","created":"2018-12-04","cited_by_count":7,"area":"offlinerl"},{"id":"1907.02140","title":"Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model","created":"2019-07-03","cited_by_count":7,"area":"offlinerl"},{"id":"2102.11387","title":"Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation","created":"2021-02-22","cited_by_count":7,"area":null},{"id":"2306.01839","title":"Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2308.09387","title":"Multi-Level Compositional Reasoning for Interactive Instruction Following","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2408.04498","title":"Model-Based Transfer Learning for Contextual Reinforcement Learning","created":"2024-08-08","cited_by_count":7,"area":"deeprl"},{"id":"2510.14837","title":"Reinforcement Learning with Stochastic Reward Machines","created":"2025-10-16","cited_by_count":7,"area":"deeprl"},{"id":"2110.04357","title":"Training Transition Policies via Distribution Matching for Complex Tasks","created":"2021-10-08","cited_by_count":6,"area":null},{"id":"2211.09937","title":"Explainability Via Causal Self-Talk","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2503.16799","title":"Causally Aligned Curriculum Learning","created":"2025-03-21","cited_by_count":6,"area":"deeprl"},{"id":"2602.17038","title":"Phase-Aware Mixture of Experts for Agentic Reinforcement Learning","created":"2026-02-19","cited_by_count":6,"area":"agents"},{"id":"2606.09316","title":"Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents","created":"2026-06-08","cited_by_count":6,"area":"rag"},{"id":"2106.13935","title":"Discovering Generalizable Skills via Automated Generation of Diverse Tasks","created":"2021-06-26","cited_by_count":5,"area":null},{"id":"2110.04649","title":"Interactive Hierarchical Guidance using Language","created":"2021-10-09","cited_by_count":5,"area":null},{"id":"2111.09475","title":"Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines","created":"2021-11-18","cited_by_count":5,"area":null},{"id":"2210.00350","title":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","created":"2022-10-01","cited_by_count":5,"area":null},{"id":"2303.05487","title":"Learning Rational Subgoals from Demonstrations and Instructions","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2503.14555","title":"A Generalist Hanabi Agent","created":"2025-03-17","cited_by_count":5,"area":"deeprl"},{"id":"2507.10741","title":"Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data","created":"2025-07-14","cited_by_count":5,"area":"agents"},{"id":"2512.21898","title":"Flexible Multitask Learning with Factorized Diffusion Policy","created":"2025-12-26","cited_by_count":5,"area":"diffusion"}],"next_cursor":"100"}