{"url":"/task/sokoban","name":"Sokoban","slug":"sokoban","description_markdown":null,"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":"derived"},"counts":{"papers_tagged":61,"papers_with_code":32,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/trajectory-planning","name":"Trajectory Planning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":32,"tagged_in_all":61,"items":[{"url":"/paper/tree-search-vs-optimization-approaches-for","title":"Tree Search vs Optimization Approaches for Map Generation","date":"2019-03-27","arxiv_id":"1903.11678","repositories_listed":5,"syntology":null},{"url":"/paper/planning-behavior-in-a-recurrent-neural","title":"Planning in a recurrent neural network that plays Sokoban","date":"2024-07-22","arxiv_id":"2407.15421","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/levin-tree-search-with-context-models","title":"Levin Tree Search with Context Models","date":"2023-05-26","arxiv_id":"2305.16945","repositories_listed":2,"syntology":null},{"url":"/paper/illuminating-diverse-neural-cellular-automata","title":"Illuminating Diverse Neural Cellular Automata for Level Generation","date":"2021-09-12","arxiv_id":"2109.05489","repositories_listed":2,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/inductive-general-game-playing","title":"Inductive general game playing","date":"2019-06-23","arxiv_id":"1906.09627","repositories_listed":2,"syntology":null},{"url":"/paper/q-map-a-convolutional-approach-for-goal","title":"Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks","date":"2018-10-06","arxiv_id":"1810.02927","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-search-with-mctsnets","title":"Learning to Search with MCTSnets","date":"2018-02-13","arxiv_id":"1802.04697","repositories_listed":2,"syntology":null},{"url":"/paper/interpreting-learned-search-finding-a","title":"Interpreting learned search: finding a transition model and value function in an RNN that plays Sokoban","date":"2025-06-11","arxiv_id":"2506.10138","repositories_listed":1,"syntology":null},{"url":"/paper/solving-sokoban-using-hierarchical-1","title":"Solving Sokoban using Hierarchical Reinforcement Learning with Landmarks","date":"2025-04-06","arxiv_id":"2504.04366","repositories_listed":1,"syntology":null},{"url":"/paper/magebench-bridging-large-multimodal-models-to","title":"MageBench: Bridging Large Multimodal Models to Agents","date":"2024-12-05","arxiv_id":"2412.04531","repositories_listed":1,"syntology":null},{"url":"/paper/learning-discrete-world-models-for-heuristic","title":"Learning Discrete World Models for Heuristic Search","date":"2024-09-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-training-data-recipe-to-accelerate-a-search","title":"A Training Data Recipe to Accelerate A* Search with Language Models","date":"2024-07-13","arxiv_id":"2407.09985","repositories_listed":1,"syntology":null},{"url":"/paper/3d-building-generation-in-minecraft-via-large","title":"3D Building Generation in Minecraft via Large Language Models","date":"2024-06-13","arxiv_id":"2406.08751","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-a-better-planning-with-transformers","title":"Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping","date":"2024-02-21","arxiv_id":"2402.14083","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_unverified":1,"n_pointer_only":14}},{"url":"/paper/on-grid-graph-reachability-and-puzzle-games","title":"On Grid Graph Reachability and Puzzle Games","date":"2023-10-02","arxiv_id":"2310.01378","repositories_listed":1,"syntology":null},{"url":"/paper/thinker-learning-to-plan-and-act-1","title":"Thinker: Learning to Plan and Act","date":"2023-07-27","arxiv_id":"2307.14993","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/start-small-training-game-level-generators","title":"Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes","date":"2022-09-29","arxiv_id":"2209.15052","repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-precise-adjusting-planning-horizon","title":"Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search","date":"2022-06-01","arxiv_id":"2206.00702","repositories_listed":1,"syntology":null},{"url":"/paper/expose-combining-state-based-exploration-with","title":"ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search","date":"2022-02-03","arxiv_id":"2202.01461","repositories_listed":1,"syntology":null},{"url":"/paper/subgoal-search-for-complex-reasoning-tasks","title":"Subgoal Search For Complex Reasoning Tasks","date":"2021-08-25","arxiv_id":"2108.11204","repositories_listed":1,"syntology":null},{"url":"/paper/classical-planning-in-deep-latent-space-1","title":"Classical Planning in Deep Latent Space","date":"2021-06-30","arxiv_id":"2107.00110","repositories_listed":1,"syntology":null},{"url":"/paper/policy-guided-heuristic-search-with","title":"Policy-Guided Heuristic Search with Guarantees","date":"2021-03-21","arxiv_id":"2103.11505","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/towards-action-model-learning-for-player","title":"Towards Action Model Learning for Player Modeling","date":"2021-03-09","arxiv_id":"2103.05682","repositories_listed":1,"syntology":null},{"url":"/paper/physically-embedded-planning-problems-new","title":"Physically Embedded Planning Problems: New Challenges for Reinforcement Learning","date":"2020-09-11","arxiv_id":"2009.05524","repositories_listed":1,"syntology":null},{"url":"/paper/mixed-initiative-level-design-with-rl-brush","title":"Mixed-Initiative Level Design with RL Brush","date":"2020-08-06","arxiv_id":"2008.02778","repositories_listed":1,"syntology":null},{"url":"/paper/solving-hard-ai-planning-instances-using","title":"Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning","date":"2020-06-04","arxiv_id":"2006.02689","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/multi-objective-level-generator-generation","title":"Multi-Objective level generator generation with Marahel","date":"2020-05-17","arxiv_id":"2005.08368","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-sensitive-learning-and-planning-1","title":"Uncertainty-sensitive Learning and Planning with Ensembles","date":"2019-12-19","arxiv_id":"1912.09996","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-sensitive-learning-and-planning","title":"Uncertainty - sensitive learning and planning with ensembles","date":"2019-09-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-local-forward-models-on-unforgiving","title":"Learning Local Forward Models on Unforgiving Games","date":"2019-09-01","arxiv_id":"1909.00442","repositories_listed":1,"syntology":null}],"syntology_records":6,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}