SOTAVerified

Sokoban

Papers

Showing 1–25 of 61 papers

TitleStatusHype
Interpreting learned search: finding a transition model and value function in an RNN that plays SokobanCode1
Solving Sokoban using Hierarchical Reinforcement Learning with LandmarksCode0
Interpreting Emergent Planning in Model-Free Reinforcement Learning—0
MageBench: Bridging Large Multimodal Models to AgentsCode1
Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach—0
Learning Discrete World Models for Heuristic SearchCode1
Planning in a recurrent neural network that plays SokobanCode1
A Training Data Recipe to Accelerate A* Search with Language ModelsCode0
Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents—0
Interpreting Multi-objective Evolutionary Algorithms via Sokoban Level Generation—0
3D Building Generation in Minecraft via Large Language ModelsCode0
AlphaZeroES: Direct score maximization outperforms planning loss minimization—0
Beyond A*: Better Planning with Transformers via Search Dynamics BootstrappingCode3
Human Goal Recognition as Bayesian Inference: Investigating the Impact of Actions, Timing, and Goal Solvability—0
PCGPT: Procedural Content Generation via Transformers—0
On Grid Graph Reachability and Puzzle GamesCode0
AI planning in the imagination: High-level planning on learned abstract search spaces—0
Thinker: Learning to Plan and ActCode1
Levin Tree Search with Context ModelsCode1
Explainable Goal Recognition: A Framework Based on Weight of Evidence—0
Level Generation Through Large Language Models—0
Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple SizesCode0
A Differentiable Loss Function for Learning Heuristics in A*—0
Keke AI Competition: Solving puzzle levels in a dynamically changing mechanic space—0
Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning—0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.