{"total":49,"rows":[{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"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":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2312.06853","title":"LLF-Bench: Benchmark for Interactive Learning from Language Feedback","created":"2023-12-11","cited_by_count":33,"area":null},{"id":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2110.10963","title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic","created":"2021-10-21","cited_by_count":30,"area":null},{"id":"2201.01251","title":"Multi-Stage Episodic Control for Strategic Exploration in Text Games","created":"2022-01-04","cited_by_count":22,"area":null},{"id":"2103.13552","title":"Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents","created":"2021-03-25","cited_by_count":20,"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":"2103.07011","title":"Towards Socially Intelligent Agents with Mental State Transition and Human Utility","created":"2021-03-12","cited_by_count":14,"area":null},{"id":"2104.09469","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2109.09478","title":"A Survey of Text Games for Reinforcement Learning informed by Natural Language","created":"2021-09-20","cited_by_count":14,"area":null},{"id":"2208.01174","title":"TextWorldExpress: Simulating Text Games at One Million Steps Per Second","created":"2022-08-01","cited_by_count":13,"area":null},{"id":"2211.04591","title":"Learning to Follow Instructions in Text-Based Games","created":"2022-11-08","cited_by_count":12,"area":null},{"id":"2405.13828","title":"Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations","created":"2024-05-22","cited_by_count":12,"area":null},{"id":"2511.13091","title":"STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization","created":"2025-11-17","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":"2504.14128","title":"TALES: Text Adventure Learning Environment Suite","created":"2025-04-19","cited_by_count":11,"area":null},{"id":"2103.02363","title":"Reinforcement Learning with External Knowledge by using Logical Neural Networks","created":"2021-03-03","cited_by_count":10,"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":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2312.04881","title":"Predictive Chemistry Augmented with Text Retrieval","created":"2023-12-08","cited_by_count":10,"area":null},{"id":"2210.00066","title":"Improving Policy Learning via Language Dynamics Distillation","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2411.13410","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","created":"2024-11-20","cited_by_count":9,"area":null},{"id":"2110.08470","title":"Case-based Reasoning for Better Generalization in Textual Reinforcement Learning","created":"2021-10-16","cited_by_count":8,"area":null},{"id":"2110.10973","title":"LOA: Logical Optimal Actions for Text-based Interaction Games","created":"2021-10-21","cited_by_count":6,"area":null},{"id":"2308.01872","title":"Thespian: Multi-Character Text Role-Playing Game Agents","created":"2023-08-03","cited_by_count":6,"area":null},{"id":"2105.04976","title":"Designing an Automatic Agent for Repeated Language based Persuasion Games","created":"2021-05-11","cited_by_count":5,"area":null},{"id":"2308.01734","title":"Ambient Adventures: Teaching ChatGPT on Developing Complex Stories","created":"2023-08-03","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2106.05387","title":"Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2307.02689","title":"Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2306.08400","title":"Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2309.11564","title":"Hierarchical reinforcement learning with natural language subgoals","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2403.10692","title":"EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning","created":"2024-03-15","cited_by_count":3,"area":null},{"id":"2606.24893","title":"AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2106.00257","title":"A Coarse to Fine Question Answering System based on Reinforcement Learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2109.13855","title":"Actionable Entities Recognition Benchmark for Interactive Fiction","created":"2021-09-28","cited_by_count":2,"area":null},{"id":"2210.08384","title":"Revisiting the Roles of \"Text\" in Text Games","created":"2022-10-15","cited_by_count":2,"area":null},{"id":"2302.10720","title":"Learning to Play Text-based Adventure Games with Maximum Entropy Reinforcement Learning","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2307.03906","title":"ScriptWorld: Text Based Environment For Learning Procedural Knowledge","created":"2023-07-08","cited_by_count":2,"area":null},{"id":"2504.06868","title":"Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games","created":"2025-04-09","cited_by_count":1,"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":"2302.12403","title":"Plume: A Framework for High Performance Deep RL Network Controllers via Prioritized Trace Sampling","created":"2023-02-24","cited_by_count":0,"area":null}],"next_cursor":null}