Browse State-of-the-Art › Sokoban
Sokoban
32 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
No dataset record in the archive lists this task.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 61 · with a code link: 32 · where Syntology ran a sample: 6 (5 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 61 tagged: 5 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 61 of 61, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
27 Mar 2019 5 repositories listedWe compare them on three different game level generation problems: Binary, Zelda, and Sokoban.
-
22 Jul 2024 2 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 1 pointer-only (licence)How a neural network (NN) generalizes to novel situations depends on whether it has learned to select actions heuristically or via a planning process.
-
26 May 2023 2 repositories listedLevin Tree Search (LTS) is a search algorithm that makes use of a policy (a probability distribution over actions) and comes with a theoretical guarantee on the number of expansions before reaching a goal node…
-
12 Sep 2021 2 repositories listed Syntology official (archive's flag): 2 ran · 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 13 harvested samples)We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels.
-
23 Jun 2019 2 repositories listedThis problem is central to inductive general game playing (IGGP).
-
6 Oct 2018 2 repositories listedBeing able to reach any desired location in the environment can be a valuable asset for an agent.
-
13 Feb 2018 2 repositories listedThey are most typically solved by tree search algorithms that simulate ahead into the future, evaluate future states, and back-up those evaluations to the root of a search tree.
-
11 Jun 2025 1 repository listedEach layer has its own plan representation and value function, increasing search depth.
-
6 Apr 2025 1 repository listedWe introduce a novel hierarchical reinforcement learning (HRL) framework that performs top-down recursive planning via learned subgoals, successfully applied to the complex combinatorial puzzle game Sokoban.
-
5 Dec 2024 1 repository listedSuch vision-in-the-chain reasoning paradigm is more aligned with the needs of multimodal agents, while being rarely evaluated.
-
14 Sep 2024 1 repository listedWhile model-based reinforcement learning methods learn world models that can then be used for planning, such approaches are limited by errors that accumulate when the model is applied across many timesteps as well as…
-
13 Jul 2024 1 repository listedCombining Large Language Models (LLMs) with heuristic search algorithms like A* holds the promise of enhanced LLM reasoning and scalable inference.
-
13 Jun 2024 1 repository listedRecently, procedural content generation has exhibited considerable advancements in the domain of 2D game level generation such as Super Mario Bros. and Sokoban through large language models (LLMs).
-
21 Feb 2024 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (of 14 harvested samples) · 14 pointer-only (licence)We fine tune this model to obtain a Searchformer, a Transformer model that optimally solves previously unseen Sokoban puzzles 93.
-
2 Oct 2023 1 repository listedMany puzzle video games, like Sokoban, involve moving some agent in a maze.
-
27 Jul 2023 1 repository listed Syntology official (archive's flag): 2 ran · 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 (of 2 harvested samples)This approach eliminates the need for handcrafted planning algorithms by enabling the agent to learn how to plan autonomously and allows for easy interpretation of the agent's plan with visualization.
-
29 Sep 2022 1 repository listedA level generator is a tool that generates game levels from noise.
-
1 Jun 2022 1 repository listedComplex reasoning problems contain states that vary in the computational cost required to determine a good action plan.
-
3 Feb 2022 1 repository listedDepending upon the smoothness of the action-value function, one approach to overcoming this issue is through online learning, where information is interpolated among similar states; Policy Gradient Search provides a…
-
25 Aug 2021 1 repository listedIn this paper, we implement kSubS using a transformer-based subgoal module coupled with the classical best-first search framework.
-
30 Jun 2021 1 repository listedCurrent domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck.
-
21 Mar 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 3 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; every one of the 3 samples that ran constructed an object rather than computing a result (of 3 harvested samples)LevinTS is guided by a policy and provides guarantees on the number of search steps that relate to the quality of the policy, but it does not make use of a heuristic function.
-
9 Mar 2021 1 repository listedIn this paper, we present our findings with using action model learning (AML), in which an action model is learned given data in the form of a play trace, to learn a player model in a domain-agnostic manner.
-
11 Sep 2020 1 repository listedTo encourage progress towards this goal we introduce a set of physically embedded planning problems and make them publicly available.
-
6 Aug 2020 1 repository listedThis paper introduces RL Brush, a level-editing tool for tile-based games designed for mixed-initiative co-creation.
-
4 Jun 2020 1 repository listed Syntology 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)Despite significant progress in general AI planning, certain domains remain out of reach of current AI planning systems.
-
17 May 2020 1 repository listedThis paper introduces a new system to design constructive level generators by searching the space of constructive level generators defined by Marahel language.
-
19 Dec 2019 1 repository listedThe former manifests itself through the use of value function, while the latter is powered by a tree search planner.
-
25 Sep 2019 1 repository listedNotably, our method performs well in environments with sparse rewards where standard TD(1) backups fail.
-
1 Sep 2019 1 repository listedThis paper examines learning approaches for forward models based on local cell transition functions.
-
11 Jan 2019 1 repository listed
-
27 Nov 2018 1 repository listed
-
Interpreting Emergent Planning in Model-Free Reinforcement Learning2 Apr 2025 0 repositories listed
-
Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach18 Sep 2024 0 repositories listed
-
Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents5 Jul 2024 0 repositories listed
-
Interpreting Multi-objective Evolutionary Algorithms via Sokoban Level Generation15 Jun 2024 0 repositories listed
-
AlphaZeroES: Direct score maximization outperforms planning loss minimization12 Jun 2024 0 repositories listed
-
Human Goal Recognition as Bayesian Inference: Investigating the Impact of Actions, Timing, and Goal Solvability16 Feb 2024 0 repositories listed
-
PCGPT: Procedural Content Generation via Transformers3 Oct 2023 0 repositories listed
-
AI planning in the imagination: High-level planning on learned abstract search spaces16 Aug 2023 0 repositories listed
-
Explainable Goal Recognition: A Framework Based on Weight of Evidence9 Mar 2023 0 repositories listed
-
Level Generation Through Large Language Models11 Feb 2023 0 repositories listed
-
A Differentiable Loss Function for Learning Heuristics in A*12 Sep 2022 0 repositories listed
-
Keke AI Competition: Solving puzzle levels in a dynamically changing mechanic space11 Sep 2022 0 repositories listed
-
Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning28 Jun 2022 0 repositories listed
-
Learning First-Order Symbolic Planning Representations That Are Grounded25 Apr 2022 0 repositories listed
-
Path of Destruction: Learning an Iterative Level Generator Using a Small Dataset21 Feb 2022 0 repositories listed
-
A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances3 Oct 2021 0 repositories listed
-
Potential-based Reward Shaping in Sokoban10 Sep 2021 0 repositories listed
-
There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning8 Jun 2021 0 repositories listed
-
Transfer Learning and Curriculum Learning in Sokoban25 May 2021 0 repositories listed
-
Solving Sokoban with forward-backward reinforcement learning5 May 2021 0 repositories listed
-
Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban3 Oct 2020 0 repositories listed
-
Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations4 Feb 2020 0 repositories listed
-
Working Memory Graphs17 Nov 2019 0 repositories listed
-
Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture30 Oct 2019 0 repositories listed
-
Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer25 Sep 2019 0 repositories listed
-
Procedural Generation of Initial States of Sokoban4 Jul 2019 0 repositories listed
-
Generalization to Novel Objects using Prior Relational Knowledge26 Jun 2019 0 repositories listed
-
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning1 Dec 2018 0 repositories listed
-
AI in Game Playing: Sokoban Solver29 Jun 2018 0 repositories listed
Syntology lines on 6 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections