| Interpreting learned search: finding a transition model and value function in an RNN that plays Sokoban | Jun 11, 2025 | Sokoban | CodeCode Available | 1 |
| Solving Sokoban using Hierarchical Reinforcement Learning with Landmarks | Apr 6, 2025 | Hierarchical Reinforcement Learningreinforcement-learning | CodeCode Available | 0 |
| Interpreting Emergent Planning in Model-Free Reinforcement Learning | Apr 2, 2025 | reinforcement-learningReinforcement Learning | —Unverified | 0 |
| MageBench: Bridging Large Multimodal Models to Agents | Dec 5, 2024 | Sokoban | CodeCode Available | 1 |
| Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach | Sep 18, 2024 | Decision MakingHuman Agent Collaboration | —Unverified | 0 |
| Learning Discrete World Models for Heuristic Search | Sep 14, 2024 | Deep Reinforcement LearningHeuristic Search | CodeCode Available | 1 |
| Planning in a recurrent neural network that plays Sokoban | Jul 22, 2024 | Sokoban | CodeCode Available | 1 |
| A Training Data Recipe to Accelerate A* Search with Language Models | Jul 13, 2024 | Heuristic SearchLanguage Modelling | CodeCode Available | 0 |
| Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents | Jul 5, 2024 | GPUImitation Learning | —Unverified | 0 |
| Interpreting Multi-objective Evolutionary Algorithms via Sokoban Level Generation | Jun 15, 2024 | DiversityEvolutionary Algorithms | —Unverified | 0 |
| 3D Building Generation in Minecraft via Large Language Models | Jun 13, 2024 | MinecraftSokoban | CodeCode Available | 0 |
| AlphaZeroES: Direct score maximization outperforms planning loss minimization | Jun 12, 2024 | SokobanValue prediction | —Unverified | 0 |
| Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping | Feb 21, 2024 | Decision MakingDecoder | CodeCode Available | 3 |
| Human Goal Recognition as Bayesian Inference: Investigating the Impact of Actions, Timing, and Goal Solvability | Feb 16, 2024 | Bayesian InferenceSokoban | —Unverified | 0 |
| PCGPT: Procedural Content Generation via Transformers | Oct 3, 2023 | Game DesignSokoban | —Unverified | 0 |
| On Grid Graph Reachability and Puzzle Games | Oct 2, 2023 | Sokoban | CodeCode Available | 0 |
| AI planning in the imagination: High-level planning on learned abstract search spaces | Aug 16, 2023 | SokobanTraveling Salesman Problem | —Unverified | 0 |
| Thinker: Learning to Plan and Act | Jul 27, 2023 | Sokoban | CodeCode Available | 1 |
| Levin Tree Search with Context Models | May 26, 2023 | Rubik's CubeSokoban | CodeCode Available | 1 |
| Explainable Goal Recognition: A Framework Based on Weight of Evidence | Mar 9, 2023 | Sokoban | —Unverified | 0 |
| Level Generation Through Large Language Models | Feb 11, 2023 | Sokoban | —Unverified | 0 |
| Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes | Sep 29, 2022 | DiversitySokoban | CodeCode Available | 0 |
| A Differentiable Loss Function for Learning Heuristics in A* | Sep 12, 2022 | Sokoban | —Unverified | 0 |
| Keke AI Competition: Solving puzzle levels in a dynamically changing mechanic space | Sep 11, 2022 | Sokoban | —Unverified | 0 |
| Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning | Jun 28, 2022 | Deep Reinforcement LearningSokoban | —Unverified | 0 |