{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/text-based-games","name":"text-based games","slug":"text-based-games","description_markdown":"Text-based games to evaluate the Reinforcement Learning Agents","categories":[{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":75,"papers_with_code":36,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/jericho","name":"Jericho","full_name":"","num_papers_in_archive":54},{"url":"/dataset/cards-against-humanity","name":"Cards Against Humanity","full_name":"","num_papers_in_archive":1},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1},{"url":"/dataset/textworld-kg","name":"TextWorld KG","full_name":null,"num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":75,"of":75,"of_with_code":36,"tagged_in_all":75,"counts":{"archive_papers_tagged":75,"with_a_code_link":36,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":75,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":5,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/deep-reinforcement-learning-with-a-natural","slug":"deep-reinforcement-learning-with-a-natural","title":"Deep Reinforcement Learning with a Natural Language Action Space","date":"2015-11-14","arxiv_id":"1511.04636","repositories_listed":3,"syntology":null},{"url":"/paper/language-understanding-for-text-based-games","slug":"language-understanding-for-text-based-games","title":"Language Understanding for Text-based Games Using Deep Reinforcement Learning","date":"2015-06-30","arxiv_id":"1506.08941","repositories_listed":3,"syntology":null},{"url":"/paper/textgames-learning-to-self-play-text-based","slug":"textgames-learning-to-self-play-text-based","title":"TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning","date":"2025-02-25","arxiv_id":"2502.18431","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/textgames-learning-to-self-play-text-based#ran","syntology_url":"https://syntology.ai/paper/2502.18431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18431"}},"official":{"repos":["fhudi/textgames"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/constructing-temporal-dynamic-knowledge","slug":"constructing-temporal-dynamic-knowledge","title":"Constructing Temporal Dynamic Knowledge Graphs from Interactive Text-based Games","date":"2023-11-03","arxiv_id":"2311.01928","repositories_listed":2,"syntology":null},{"url":"/paper/textworldexpress-simulating-text-games-at-one","slug":"textworldexpress-simulating-text-games-at-one","title":"TextWorldExpress: Simulating Text Games at One Million Steps Per Second","date":"2022-08-01","arxiv_id":"2208.01174","repositories_listed":2,"syntology":null},{"url":"/paper/text-based-rl-agents-with-commonsense","slug":"text-based-rl-agents-with-commonsense","title":"Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines","date":"2020-10-08","arxiv_id":"2010.03790","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/text-based-rl-agents-with-commonsense#ran","syntology_url":"https://syntology.ai/paper/2010.03790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03790"}},"official":{"repos":["IBM/commonsense-rl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/counting-to-explore-and-generalize-in-text","slug":"counting-to-explore-and-generalize-in-text","title":"Counting to Explore and Generalize in Text-based Games","date":"2018-06-29","arxiv_id":"1806.11525","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/counting-to-explore-and-generalize-in-text#ran","syntology_url":"https://syntology.ai/paper/1806.11525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.11525"}},"official":{"repos":["xingdi-eric-yuan/TextWorld-Coin-Collector"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/using-reinforcement-learning-to-learn-how-to","slug":"using-reinforcement-learning-to-learn-how-to","title":"Using reinforcement learning to learn how to play text-based games","date":"2018-01-06","arxiv_id":"1801.01999","repositories_listed":2,"syntology":null},{"url":"/paper/situatedthinker-grounding-llm-reasoning-with","slug":"situatedthinker-grounding-llm-reasoning-with","title":"SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking","date":"2025-05-25","arxiv_id":"2505.19300","repositories_listed":1,"syntology":null},{"url":"/paper/textarena","slug":"textarena","title":"TextArena","date":"2025-04-15","arxiv_id":"2504.11442","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/textarena#ran","syntology_url":"https://syntology.ai/paper/2504.11442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11442"}},"official":{"repos":["leonguertler/textarena"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/persona-dynamics-unveiling-the-impact-of","slug":"persona-dynamics-unveiling-the-impact-of","title":"Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games","date":"2025-04-09","arxiv_id":"2504.06868","repositories_listed":1,"syntology":null},{"url":"/paper/starling-self-supervised-training-of-text","slug":"starling-self-supervised-training-of-text","title":"STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models","date":"2024-06-09","arxiv_id":"2406.05872","repositories_listed":1,"syntology":null},{"url":"/paper/explorer-exploration-guided-reasoning-for","slug":"explorer-exploration-guided-reasoning-for","title":"EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning","date":"2024-03-15","arxiv_id":"2403.10692","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-neurosymbolic","slug":"large-language-models-are-neurosymbolic","title":"Large Language Models Are Neurosymbolic Reasoners","date":"2024-01-17","arxiv_id":"2401.09334","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-are-neurosymbolic#ran","syntology_url":"https://syntology.ai/paper/2401.09334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09334"}},"official":{"repos":["hyintell/llmsymbolic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scriptworld-text-based-environment-for","slug":"scriptworld-text-based-environment-for","title":"ScriptWorld: Text Based Environment For Learning Procedural Knowledge","date":"2023-07-08","arxiv_id":"2307.03906","repositories_listed":1,"syntology":null},{"url":"/paper/bytesized32-a-corpus-and-challenge-task-for","slug":"bytesized32-a-corpus-and-challenge-task-for","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","date":"2023-05-24","arxiv_id":"2305.14879","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bytesized32-a-corpus-and-challenge-task-for#ran","syntology_url":"https://syntology.ai/paper/2305.14879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14879"}},"official":{"repos":["cognitiveailab/bytesized32"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-minimal-approach-for-natural-language","slug":"a-minimal-approach-for-natural-language","title":"A Minimal Approach for Natural Language Action Space in Text-based Games","date":"2023-05-06","arxiv_id":"2305.04082","repositories_listed":1,"syntology":null},{"url":"/paper/learn-what-is-possible-then-choose-what-is","slug":"learn-what-is-possible-then-choose-what-is","title":"Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games","date":"2023-04-14","arxiv_id":"2304.07258","repositories_listed":1,"syntology":null},{"url":"/paper/potential-based-reward-shaping-for-learning","slug":"potential-based-reward-shaping-for-learning","title":"Learning to Play Text-based Adventure Games with Maximum Entropy Reinforcement Learning","date":"2023-02-21","arxiv_id":"2302.10720","repositories_listed":1,"syntology":null},{"url":"/paper/diffg-rl-leveraging-difference-between-state","slug":"diffg-rl-leveraging-difference-between-state","title":"DiffG-RL: Leveraging Difference between State and Common Sense","date":"2022-11-29","arxiv_id":"2211.16002","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-follow-instructions-in-text-based","slug":"learning-to-follow-instructions-in-text-based","title":"Learning to Follow Instructions in Text-Based Games","date":"2022-11-08","arxiv_id":"2211.04591","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-follow-instructions-in-text-based#ran","syntology_url":"https://syntology.ai/paper/2211.04591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.04591"}},"official":{"repos":["mathieutuli/ltl-gata"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fire-burns-sword-cuts-commonsense-inductive","slug":"fire-burns-sword-cuts-commonsense-inductive","title":"Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/perceiving-the-world-question-guided","slug":"perceiving-the-world-question-guided","title":"Perceiving the World: Question-guided Reinforcement Learning for Text-based Games","date":"2022-03-20","arxiv_id":"2204.09597","repositories_listed":1,"syntology":null},{"url":"/paper/neuro-symbolic-approaches-for-text-based","slug":"neuro-symbolic-approaches-for-text-based","title":"Neuro-Symbolic Approaches for Text-Based Policy Learning","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/loa-logical-optimal-actions-for-text-based-1","slug":"loa-logical-optimal-actions-for-text-based-1","title":"LOA: Logical Optimal Actions for Text-based Interaction Games","date":"2021-10-21","arxiv_id":"2110.10973","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-in-text-based-games-via","slug":"generalization-in-text-based-games-via","title":"Generalization in Text-based Games via Hierarchical Reinforcement Learning","date":"2021-09-21","arxiv_id":"2109.09968","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalization-in-text-based-games-via#ran","syntology_url":"https://syntology.ai/paper/2109.09968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09968"}},"official":{"repos":["yunqiuxu/h-kga"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pre-trained-language-models-as-prior","slug":"pre-trained-language-models-as-prior","title":"Pre-trained Language Models as Prior Knowledge for Playing Text-based Games","date":"2021-07-18","arxiv_id":"2107.08408","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-with-stacked","slug":"deep-reinforcement-learning-with-stacked","title":"Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games","date":"2020-10-22","arxiv_id":"2010.11655","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-reinforcement-learning-with-stacked#ran","syntology_url":"https://syntology.ai/paper/2010.11655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11655"}},"official":{"repos":["YunqiuXu/SHA-KG"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/keep-calm-and-explore-language-models-for","slug":"keep-calm-and-explore-language-models-for","title":"Keep CALM and Explore: Language Models for Action Generation in Text-based Games","date":"2020-10-06","arxiv_id":"2010.02903","repositories_listed":1,"syntology":null},{"url":"/paper/bootstrapped-q-learning-with-context-relevant","slug":"bootstrapped-q-learning-with-context-relevant","title":"Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games","date":"2020-09-24","arxiv_id":"2009.11896","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-avoid-being-eaten-by-a-grue-structured","slug":"how-to-avoid-being-eaten-by-a-grue-structured","title":"How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds","date":"2020-06-12","arxiv_id":"2006.07409","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/how-to-avoid-being-eaten-by-a-grue-structured#ran","syntology_url":"https://syntology.ai/paper/2006.07409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07409"}},"official":{"repos":["rajammanabrolu/Q-BERT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/learning-dynamic-knowledge-graphs-to","slug":"learning-dynamic-knowledge-graphs-to","title":"Learning Dynamic Belief Graphs to Generalize on Text-Based Games","date":"2020-02-21","arxiv_id":"2002.09127","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-avoid-being-eaten-by-a-grue","slug":"how-to-avoid-being-eaten-by-a-grue","title":"How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents","date":"2020-02-19","arxiv_id":"2002.08795","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-to-avoid-being-eaten-by-a-grue#ran","syntology_url":"https://syntology.ai/paper/2002.08795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.08795"}},"official":{"repos":["rajammanabrolu/Q-BERT"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/building-dynamic-knowledge-graphs-from-text-2","slug":"building-dynamic-knowledge-graphs-from-text-2","title":"Building Dynamic Knowledge Graphs from Text-based Games","date":"2019-10-21","arxiv_id":"1910.09532","repositories_listed":1,"syntology":null},{"url":"/paper/towards-solving-text-based-games-by-producing","slug":"towards-solving-text-based-games-by-producing","title":"Towards Solving Text-based Games by Producing Adaptive Action Spaces","date":"2018-12-03","arxiv_id":"1812.00855","repositories_listed":1,"syntology":null},{"url":"/paper/textworld-a-learning-environment-for-text","slug":"textworld-a-learning-environment-for-text","title":"TextWorld: A Learning Environment for Text-based Games","date":"2018-06-29","arxiv_id":"1806.11532","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/textworld-a-learning-environment-for-text#ran","syntology_url":"https://syntology.ai/paper/1806.11532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.11532"}},"official":null}},{"url":null,"slug":"monte-carlo-planning-with-large-language","title":"Monte Carlo Planning with Large Language Model for Text-Based Game Agents","date":"2025-04-23","arxiv_id":"2504.16855","repositories_listed":0,"syntology":null},{"url":null,"slug":"positive-experience-reflection-for-agents-in","title":"Positive Experience Reflection for Agents in Interactive Text Environments","date":"2024-11-04","arxiv_id":"2411.02223","repositories_listed":0,"syntology":null},{"url":null,"slug":"malinowski-in-the-age-of-ai-can-large","title":"Malinowski in the Age of AI: Can large language models create a text game based on an anthropological classic?","date":"2024-10-27","arxiv_id":"2410.20536","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-than-your-teacher-llm-agents-that","title":"Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback","date":"2024-10-07","arxiv_id":"2410.05434","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-have-thirteen-hours-in-which-to-solve-the","title":"You Have Thirteen Hours in Which to Solve the Labyrinth: Enhancing AI Game Masters with Function Calling","date":"2024-09-11","arxiv_id":"2409.06949","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-bug-detection-in-llm-powered-text","title":"Automatic Bug Detection in LLM-Powered Text-Based Games Using LLMs","date":"2024-06-06","arxiv_id":"2406.04482","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-in-the-loop-data-optimal","title":"Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games","date":"2023-11-13","arxiv_id":"2311.07687","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-enhanced-agents-for-interactive","title":"Knowledge-enhanced Agents for Interactive Text Games","date":"2023-05-08","arxiv_id":"2305.05091","repositories_listed":0,"syntology":null},{"url":null,"slug":"story-shaping-teaching-agents-human-like","title":"Story Shaping: Teaching Agents Human-like Behavior with Stories","date":"2023-01-24","arxiv_id":"2301.10107","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-transforming-reinforcement-learning-by","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","date":"2022-12-29","arxiv_id":"2212.14164","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automating-codenames-spymasters-with","title":"Towards automating Codenames spymasters with deep reinforcement learning","date":"2022-12-28","arxiv_id":"2212.14104","repositories_listed":0,"syntology":null},{"url":null,"slug":"commonsense-knowledge-from-scene-graphs-for","title":"Commonsense Knowledge from Scene Graphs for Textual Environments","date":"2022-10-19","arxiv_id":"2210.14162","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-deep-reinforcement-learning","title":"An Analysis of Deep Reinforcement Learning Agents for Text-based Games","date":"2022-09-09","arxiv_id":"2209.04105","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sequence-modelling-approach-to-question","title":"A Sequence Modelling Approach to Question Answering in Text-Based Games","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-to-social-norms-and-values-in","title":"Aligning to Social Norms and Values in Interactive Narratives","date":"2022-05-04","arxiv_id":"2205.01975","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-two-step-hybrid-policy-for-graph-1","title":"Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning","date":"2022-01-21","arxiv_id":"2201.08520","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-neuro-symbolic-approach-for-text","title":"A Hybrid Neuro-Symbolic approach for Text-Based Games using Inductive Logic Programming","date":"2021-11-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-reinforcement-learning-with","title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic","date":"2021-10-21","arxiv_id":"2110.10963","repositories_listed":0,"syntology":null},{"url":null,"slug":"case-based-reasoning-for-better-1","title":"Case-based Reasoning for Better Generalization in Textual Reinforcement Learning","date":"2021-10-16","arxiv_id":"2110.08470","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-randomization-for-playing-text-based","title":"Goal Randomization for Playing Text-based Games without a Reward Function","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-object-oriented-dynamics-for","title":"Learning Object-Oriented Dynamics for Planning from Text","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-text-based-reinforcement-learning","title":"Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-for-mastering","title":"Meta-Reinforcement Learning for Mastering Multiple Skills and Generalizing across Environments in Text-based Games","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/learning-knowledge-graph-based-world-models","slug":"learning-knowledge-graph-based-world-models","title":"Learning Knowledge Graph-based World Models of Textual Environments","date":"2021-06-17","arxiv_id":"2106.09608","repositories_listed":0,"syntology":null},{"url":null,"slug":"eye-of-the-beholder-improved-relation","title":"Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents","date":"2021-06-09","arxiv_id":"2106.05387","repositories_listed":0,"syntology":null},{"url":null,"slug":"reading-and-acting-while-blindfolded-the-need","title":"Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents","date":"2021-03-25","arxiv_id":"2103.13552","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-text-based-reinforcement-learning-1","title":"Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations","date":"2021-02-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"playing-text-based-games-with-common-sense","title":"Playing Text-Based Games with Common Sense","date":"2020-12-04","arxiv_id":"2012.02757","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualhints-a-visual-lingual-environment-for","title":"VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning","date":"2020-10-26","arxiv_id":"2010.13839","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-analysis-for-reinforcement-learning","title":"Sentiment Analysis for Reinforcement Learning","date":"2020-10-05","arxiv_id":"2010.02316","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-based-rl-agents-with-commonsense-1","title":"Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Approaches","date":"2020-07-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-based-language-learning-for-text-1","title":"Exploration Based Language Learning for Text-Based Games","date":"2020-01-24","arxiv_id":"2001.08868","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithmic-improvements-for-deep","title":"Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction","date":"2019-11-28","arxiv_id":"1911.12511","repositories_listed":0,"syntology":null},{"url":null,"slug":"ledeepchef-deep-reinforcement-learning-agent","title":"LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games","date":"2019-09-04","arxiv_id":"1909.01646","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-assembly-sparse-imitation-learning-for","title":"Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces","date":"2019-05-23","arxiv_id":"1905.09700","repositories_listed":0,"syntology":null},{"url":null,"slug":"baselines-for-reinforcement-learning-in-text","title":"Baselines for Reinforcement Learning in Text Games","date":"2018-11-07","arxiv_id":"1811.02872","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-what-not-to-learn-action-elimination","title":"Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning","date":"2018-09-06","arxiv_id":"1809.02121","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-expansion-in-text-based-games","title":"Language Expansion In Text-Based Games","date":"2018-05-17","arxiv_id":"1805.07274","repositories_listed":0,"syntology":null},{"url":null,"slug":"playing-with-embeddings-evaluating-embeddings","title":"Playing with Embeddings : Evaluating embeddings for Robot Language Learning through MUD Games","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":12,"papers_where_code_ran_first_page":"/task/text-based-games/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/text-based-games/papers/ran/1","json":"/task/text-based-games/papers/ran/1.json","rows":12}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"eba380761a4b17240c341a95ed6bfd6920b02765f27756ce06e6e4a180cbb985","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}