{"total":80,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150,"area":"alignment"},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463,"area":"alignment"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312,"area":"lr"},{"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":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130,"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":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2107.05612","title":"A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution","created":"2021-07-12","cited_by_count":91,"area":null},{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74,"area":null},{"id":"2211.11736","title":"Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models","created":"2022-11-21","cited_by_count":58,"area":"mllm"},{"id":"2406.14596","title":"VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought","created":"2024-06-20","cited_by_count":55,"area":"lr"},{"id":"2204.02515","title":"Inferring Rewards from Language in Context","created":"2022-04-05","cited_by_count":50,"area":null},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49,"area":null},{"id":"2405.20495","title":"Transfer Q Star: Principled Decoding for LLM Alignment","created":"2024-05-30","cited_by_count":48,"area":"alignment"},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"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":"2103.05825","title":"ELLA: Exploration through Learned Language Abstraction","created":"2021-03-10","cited_by_count":42,"area":null},{"id":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41,"area":"alignment"},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37,"area":"alignment"},{"id":"2312.06853","title":"LLF-Bench: Benchmark for Interactive Learning from Language Feedback","created":"2023-12-11","cited_by_count":33,"area":null},{"id":"2301.12507","title":"Distilling Internet-Scale Vision-Language Models into Embodied Agents","created":"2023-01-29","cited_by_count":30,"area":"mllm"},{"id":"2111.03205","title":"LILA: Language-Informed Latent Actions","created":"2021-11-05","cited_by_count":27,"area":null},{"id":"2206.13074","title":"Leveraging Language for Accelerated Learning of Tool Manipulation","created":"2022-06-27","cited_by_count":26,"area":null},{"id":"2305.17608","title":"Reward Collapse in Aligning Large Language Models","created":"2023-05-28","cited_by_count":24,"area":"alignment"},{"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":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2008.06924","title":"Inverse Reinforcement Learning with Natural Language Goals","created":"2020-08-16","cited_by_count":20,"area":"offlinerl"},{"id":"2210.15629","title":"Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks","created":"2022-10-27","cited_by_count":20,"area":"diffusion"},{"id":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","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":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2206.01134","title":"Language and Culture Internalisation for Human-Like Autotelic AI","created":"2022-06-02","cited_by_count":14,"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":"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":"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":"2309.01352","title":"Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning","created":"2023-09-04","cited_by_count":9,"area":"lr"},{"id":"2303.05069","title":"Conceptual Reinforcement Learning for Language-Conditioned Tasks","created":"2023-03-09","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":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2102.11387","title":"Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation","created":"2021-02-22","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":"2203.13553","title":"Preprocessing Reward Functions for Interpretability","created":"2022-03-25","cited_by_count":7,"area":"alignment"},{"id":"2312.02206","title":"Axiomatic Preference Modeling for Longform Question Answering","created":"2023-12-02","cited_by_count":6,"area":"alignment"},{"id":"2110.04649","title":"Interactive Hierarchical Guidance using Language","created":"2021-10-09","cited_by_count":5,"area":null},{"id":"2201.08102","title":"Safe Deep RL in 3D Environments using Human Feedback","created":"2022-01-20","cited_by_count":5,"area":"alignment"},{"id":"2212.09917","title":"Inverse Reinforcement Learning for Text Summarization","created":"2022-12-19","cited_by_count":5,"area":null},{"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":"2002.00412","title":"Combating False Negatives in Adversarial Imitation Learning","created":"2020-02-02","cited_by_count":4,"area":"offlinerl"},{"id":"2101.07140","title":"Natural Language Specification of Reinforcement Learning Policies through Differentiable Decision Trees","created":"2021-01-18","cited_by_count":4,"area":null},{"id":"2102.13195","title":"Reinforcement Learning of Implicit and Explicit Control Flow in Instructions","created":"2021-02-25","cited_by_count":4,"area":null},{"id":"2104.03946","title":"Learning What To Do by Simulating the Past","created":"2021-04-08","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":"2208.06448","title":"RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents","created":"2022-08-12","cited_by_count":4,"area":null},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2503.12358","title":"IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation","created":"2025-03-16","cited_by_count":4,"area":"deeprl"},{"id":"2506.22365","title":"Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation","created":"2025-06-27","cited_by_count":4,"area":"deeprl"},{"id":"2112.07342","title":"Learning to Guide and to Be Guided in the Architect-Builder Problem","created":"2021-12-14","cited_by_count":3,"area":null},{"id":"2608.30640","title":"Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL","created":"2026-08-31","cited_by_count":3,"area":"deeprl"},{"id":"2401.02991","title":"GLIDE-RL: Grounded Language Instruction through DEmonstration in RL","created":"2024-01-03","cited_by_count":2,"area":"alignment"},{"id":"2409.18538","title":"A Survey on Complex Tasks for Goal-Directed Interactive Agents","created":"2024-09-27","cited_by_count":2,"area":"agents"},{"id":"2208.08374","title":"A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting","created":"2022-08-17","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":"2309.11753","title":"Improve the efficiency of deep reinforcement learning through semantic exploration guided by natural language","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2412.06877","title":"The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2501.15270","title":"Inductive Biases for Zero-shot Systematic Generalization in Language-informed Reinforcement Learning","created":"2025-01-25","cited_by_count":1,"area":"alignment"},{"id":"2107.09285","title":"Neural Abstructions: Abstractions that Support Construction for Grounded Language Learning","created":"2021-07-20","cited_by_count":0,"area":null},{"id":"2109.02332","title":"Hindsight Reward Tweaking via Conditional Deep Reinforcement Learning","created":"2021-09-06","cited_by_count":0,"area":null},{"id":"2110.06477","title":"Feudal Reinforcement Learning by Reading Manuals","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2202.00466","title":"Learning Invariable Semantical Representation from Language for Extensible Policy Generalization","created":"2022-01-26","cited_by_count":0,"area":null},{"id":"2402.15826","title":"Reward Design for Justifiable Sequential Decision-Making","created":"2024-02-24","cited_by_count":0,"area":"alignment"},{"id":"2409.16024","title":"From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models","created":"2024-09-24","cited_by_count":0,"area":"mllm"},{"id":"2412.07177","title":"Effective Reward Specification in Deep Reinforcement Learning","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2511.19885","title":"Complex Instruction Following with Diverse Style Policies in Football Games","created":"2025-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2512.01616","title":"CLIP-RL: Aligning Language and Policy Representations for Task Transfer in Reinforcement Learning","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2607.18258","title":"S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF","created":"2026-05-15","cited_by_count":0,"area":"alignment"},{"id":"2607.18719","title":"Strategy-Following Multi-Agent Deep Reinforcement Learning Considering Control Strategies Provided to Other Agents","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.08273","title":"Action- and Language-Conditioned Video Assessment for Embodied Control","created":"2026-08-08","cited_by_count":0,"area":null}],"next_cursor":null}