Sokoban

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

Most implemented papers archive 2025-07-28

30 shown of 32 papers with code (61 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Tree Search vs Optimization Approaches for Map Generation
  27 Mar 2019 5 repositories listed
  We compare them on three different game level generation problems: Binary, Zelda, and Sokoban.
• Planning in a recurrent neural network that plays Sokoban
  22 Jul 2024 2 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 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.
• Levin Tree Search with Context Models
  26 May 2023 2 repositories listed
  Levin 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,…
• Illuminating Diverse Neural Cellular Automata for Level Generation
  12 Sep 2021 2 repositories listed Syntology ran 2 of 13 samples · 11 unverified
  We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels.
• Inductive general game playing
  23 Jun 2019 2 repositories listed
  This problem is central to inductive general game playing (IGGP).
• Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
  6 Oct 2018 2 repositories listed
  Being able to reach any desired location in the environment can be a valuable asset for an agent.
• Learning to Search with MCTSnets
  13 Feb 2018 2 repositories listed
  They 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.
• Interpreting learned search: finding a transition model and value function in an RNN that plays Sokoban
  11 Jun 2025 1 repository listed
  Each layer has its own plan representation and value function, increasing search depth.
• Solving Sokoban using Hierarchical Reinforcement Learning with Landmarks
  6 Apr 2025 1 repository listed
  We 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.
• MageBench: Bridging Large Multimodal Models to Agents
  5 Dec 2024 1 repository listed
  Such vision-in-the-chain reasoning paradigm is more aligned with the needs of multimodal agents, while being rarely evaluated.
• Learning Discrete World Models for Heuristic Search
  14 Sep 2024 1 repository listed
  While 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…
• A Training Data Recipe to Accelerate A* Search with Language Models
  13 Jul 2024 1 repository listed
  Combining Large Language Models (LLMs) with heuristic search algorithms like A* holds the promise of enhanced LLM reasoning and scalable inference.
• 3D Building Generation in Minecraft via Large Language Models
  13 Jun 2024 1 repository listed
  Recently, procedural content generation has exhibited considerable advancements in the domain of 2D game level generation such as Super Mario Bros.
• Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
  21 Feb 2024 1 repository listed Syntology ran 13 of 14 samples · 1 unverified · 14 pointer-only (licence)
  We fine tune this model to obtain a Searchformer, a Transformer model that optimally solves previously unseen Sokoban puzzles 93.
• On Grid Graph Reachability and Puzzle Games
  2 Oct 2023 1 repository listed
  Many puzzle video games, like Sokoban, involve moving some agent in a maze.
• Thinker: Learning to Plan and Act
  27 Jul 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  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.
• Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes
  29 Sep 2022 1 repository listed
  A level generator is a tool that generates game levels from noise.
• Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
  1 Jun 2022 1 repository listed
  Complex reasoning problems contain states that vary in the computational cost required to determine a good action plan.
• ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search
  3 Feb 2022 1 repository listed
  Depending 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…
• Subgoal Search For Complex Reasoning Tasks
  25 Aug 2021 1 repository listed
  In this paper, we implement kSubS using a transformer-based subgoal module coupled with the classical best-first search framework.
• Classical Planning in Deep Latent Space
  30 Jun 2021 1 repository listed
  Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck.
• Policy-Guided Heuristic Search with Guarantees
  21 Mar 2021 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  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.
• Towards Action Model Learning for Player Modeling
  9 Mar 2021 1 repository listed
  In 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.
• Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
  11 Sep 2020 1 repository listed
  To encourage progress towards this goal we introduce a set of physically embedded planning problems and make them publicly available.
• Mixed-Initiative Level Design with RL Brush
  6 Aug 2020 1 repository listed
  This paper introduces RL Brush, a level-editing tool for tile-based games designed for mixed-initiative co-creation.
• Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning
  4 Jun 2020 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Despite significant progress in general AI planning, certain domains remain out of reach of current AI planning systems.
• Multi-Objective level generator generation with Marahel
  17 May 2020 1 repository listed
  This paper introduces a new system to design constructive level generators by searching the space of constructive level generators defined by Marahel language.
• Uncertainty-sensitive Learning and Planning with Ensembles
  19 Dec 2019 1 repository listed
  The former manifests itself through the use of value function, while the latter is powered by a tree search planner.
• Uncertainty - sensitive learning and planning with ensembles
  25 Sep 2019 1 repository listed
  Notably, our method performs well in environments with sparse rewards where standard TD(1) backups fail.
• Learning Local Forward Models on Unforgiving Games
  1 Sep 2019 1 repository listed
  This paper examines learning approaches for forward models based on local cell transition functions.

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. Read from the graph 2026-09-24.