SOTAVerified

Sokoban

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 61 papers

TitleStatusHype
Beyond A*: Better Planning with Transformers via Search Dynamics BootstrappingCode3
Interpreting learned search: finding a transition model and value function in an RNN that plays SokobanCode1
Subgoal Search For Complex Reasoning TasksCode1
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal SearchCode1
Thinker: Learning to Plan and ActCode1
Learning Discrete World Models for Heuristic SearchCode1
Tree Search vs Optimization Approaches for Map GenerationCode1
Policy-Guided Heuristic Search with GuaranteesCode1
Learning to Search with MCTSnetsCode1
Illuminating Diverse Neural Cellular Automata for Level GenerationCode1
Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement LearningCode1
Levin Tree Search with Context ModelsCode1
MageBench: Bridging Large Multimodal Models to AgentsCode1
Planning in a recurrent neural network that plays SokobanCode1
Classical Planning in Deep Latent SpaceCode1
Multi-Objective level generator generation with MarahelCode1
Learning First-Order Symbolic Planning Representations That Are Grounded—0
Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning—0
Level Generation Through Large Language Models—0
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning—0
A Differentiable Loss Function for Learning Heuristics in A*—0
AI in Game Playing: Sokoban Solver—0
AlphaZeroES: Direct score maximization outperforms planning loss minimization—0
A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances—0
Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents—0
Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban—0
Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations—0
Explainable Goal Recognition: A Framework Based on Weight of Evidence—0
Generalization to Novel Objects using Prior Relational Knowledge—0
Human Goal Recognition as Bayesian Inference: Investigating the Impact of Actions, Timing, and Goal Solvability—0
Interpreting Emergent Planning in Model-Free Reinforcement Learning—0
Interpreting Multi-objective Evolutionary Algorithms via Sokoban Level Generation—0
Keke AI Competition: Solving puzzle levels in a dynamically changing mechanic space—0
Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture—0
Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer—0
Path of Destruction: Learning an Iterative Level Generator Using a Small Dataset—0
PCGPT: Procedural Content Generation via Transformers—0
AI planning in the imagination: High-level planning on learned abstract search spaces—0
Potential-based Reward Shaping in Sokoban—0
Procedural Generation of Initial States of Sokoban—0
Solving Sokoban with forward-backward reinforcement learning—0
There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning—0
Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach—0
Transfer Learning and Curriculum Learning in Sokoban—0
Working Memory Graphs—0
Single-Agent Policy Tree Search With GuaranteesCode0
Inductive general game playingCode0
Solving Sokoban using Hierarchical Reinforcement Learning with LandmarksCode0
An investigation of model-free planningCode0
Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple SizesCode0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.