Papers with Code 아카이브

Decision Making

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

2

보존된 평가 기록

2

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/microsoft/EDDI

공식 코드

EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE

https://github.com/microsoft/alympics

공식 코드

ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents

https://github.com/microsoft/causica

공식 코드

AVID: Adapting Video Diffusion Models to World Models

https://github.com/microsoft/everything-of-thoughts-xot-

공식 코드

Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation

https://github.com/microsoft/gotflow

공식 코드

Graph-of-Thought: Utilizing Large Language Models to Solve Complex and Dynamic Business Problems

https://github.com/microsoft/horseshoe-bnn

공식 코드

Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care

https://github.com/microsoft/med-deadend

공식 코드

Medical Dead-ends and Learning to Identify High-risk States and Treatments

https://github.com/microsoft/opendatasheets-framework

공식 코드

Open Datasheets: Machine-readable Documentation for Open Datasets and Responsible AI Assessments

https://github.com/microsoft/rl-offline-simulation

공식 코드

Towards Data-Driven Offline Simulations for Online Reinforcement Learning

https://github.com/microsoft/segar

공식 코드

The Sandbox Environment for Generalizable Agent Research (SEGAR)

https://github.com/microsoft/smart

공식 코드

Position: Foundation Agents as the Paradigm Shift for Decision Making

https://github.com/microsoft/tora

공식 코드

ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving

https://github.com/migvega/bimcap

공식 코드

BIMCaP: BIM-based AI-supported LiDAR-Camera Pose Refinement

https://github.com/miilab-mtu/crt_multistageml_uncertainty

공식 코드

A new method of modeling the multi-stage decision-making process of CRT using machine learning with uncertainty quantification

https://github.com/miken1990/ir-pft

공식 코드

Previous Knowledge Utilization In Online Anytime Belief Space Planning

https://github.com/mikezchi/dcrnn-rv

공식 코드

Global Stock Market Volatility Forecasting Incorporating Dynamic Graphs and All Trading Days

https://github.com/mila-iqia/babyai

공식 코드

BabyAI 1.1

https://github.com/mila-iqia/delusions

공식 코드

Rejecting Hallucinated State Targets during Planning

https://github.com/mila-iqia/skipper

공식 코드

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning

https://github.com/mims-harvard/ToolUniverse

공식 코드

TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools

https://github.com/mims-harvard/TxAgent

공식 코드

TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools

https://github.com/mingfeisun/agail

공식 코드

Adversarial Imitation Learning from Incomplete Demonstrations

https://github.com/mingfeisun/d2-imitation

공식 코드

Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency

https://github.com/mingxuts/multi-center-fed-learning

공식 코드

Multi-Center Federated Learning: Clients Clustering for Better Personalization

https://github.com/mingyuj666/disentangling-memory-and-reasoning

공식 코드

Disentangling Memory and Reasoning Ability in Large Language Models

https://github.com/mingyuj666/simulating-alien-civilizations-with-llm-based-agents

공식 코드

What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents

https://github.com/mingzhangPHD/Adversarial-Imitation-Learning

공식 코드

Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration

https://github.com/minh-nghia/AE-1SVM

공식 코드

Scalable and Interpretable One-class SVMs with Deep Learning and Random Fourier features

https://github.com/minimaxbrl/minimax-bayes-rl

공식 코드

Minimax-Bayes Reinforcement Learning

https://github.com/minorjerry/openwebvoyager

공식 코드

OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization

https://github.com/mipt-oulu/climat

공식 코드

CLIMAT: Clinically-Inspired Multi-Agent Transformers for Knee Osteoarthritis Trajectory Forecasting

https://github.com/miriamcobo/multitasklearning_ich_prognosis

공식 코드

Multi-task Learning Approach for Intracranial Hemorrhage Prognosis

https://github.com/mirsayedshah/AI-coherent-data-driven-forecasting-model-for-a-combined-cycle-power-plant

공식 코드

AI-coherent data-driven forecasting model for a combined cycle power plant

https://github.com/mit-acl/gym-collision-avoidance

공식 코드

Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning

https://github.com/mit-ccrg/ebcl

공식 코드

Event-Based Contrastive Learning for Medical Time Series

https://github.com/mit-drl/deepdrone-public

공식 코드

Causal Navigation by Continuous-time Neural Networks

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.