Papers with Code 아카이브
Sokoban
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Solving Sokoban using Hierarchical Reinforcement Learning with Landmarks
Interpreting Emergent Planning in Model-Free Reinforcement Learning
MageBench: Bridging Large Multimodal Models to Agents
Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach
Planning in a recurrent neural network that plays Sokoban
A Training Data Recipe to Accelerate A* Search with Language Models
Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents
Interpreting Multi-objective Evolutionary Algorithms via Sokoban Level Generation
3D Building Generation in Minecraft via Large Language Models
AlphaZeroES: Direct score maximization outperforms planning loss minimization
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Human Goal Recognition as Bayesian Inference: Investigating the Impact of Actions, Timing, and Goal Solvability
PCGPT: Procedural Content Generation via Transformers
On Grid Graph Reachability and Puzzle Games
AI planning in the imagination: High-level planning on learned abstract search spaces
Thinker: Learning to Plan and Act
Levin Tree Search with Context Models
Explainable Goal Recognition: A Framework Based on Weight of Evidence
Level Generation Through Large Language Models
Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes
A Differentiable Loss Function for Learning Heuristics in A*
Keke AI Competition: Solving puzzle levels in a dynamically changing mechanic space
Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
Learning First-Order Symbolic Planning Representations That Are Grounded
Path of Destruction: Learning an Iterative Level Generator Using a Small Dataset
ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search
A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances
Illuminating Diverse Neural Cellular Automata for Level Generation
Potential-based Reward Shaping in Sokoban
Subgoal Search For Complex Reasoning Tasks
Classical Planning in Deep Latent Space
There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning
Transfer Learning and Curriculum Learning in Sokoban
Solving Sokoban with forward-backward reinforcement learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.