Papers with Code 아카이브
Efficient Exploration
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Efficient Exploration is one of the main obstacles in scaling up modern deep reinforcement learning algorithms. The main challenge in Efficient Exploration is the balance between exploiting current estimates, and gaining information about poorly understood states and actions.
Source: Randomized Value Functions via Multiplicative Normalizing Flows
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Go-Browse: Training Web Agents with Structured Exploration
DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experience
WoMAP: World Models For Embodied Open-Vocabulary Object Localization
MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming
HelixDesign-Binder: A Scalable Production-Grade Platform for Binder Design Built on HelixFold3
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
STAR-R1: Spacial TrAnsformation Reasoning by Reinforcing Multimodal LLMs
Comparative Analysis of Black-Box Optimization Methods for Weather Intervention Design
IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning
Distilling Realizable Students from Unrealizable Teachers
Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?
Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning
Interpretable SHAP-bounded Bayesian Optimization for Underwater Acoustic Metamaterial Coating Design
An Explainable Nature-Inspired Framework for Monkeypox Diagnosis: Xception Features Combined with NGBoost and African Vultures Optimization Algorithm
ForesightNav: Learning Scene Imagination for Efficient Exploration
Aerial Active STAR-RIS-assisted Satellite-Terrestrial Covert Communications
Lumos: Efficient Performance Modeling and Estimation for Large-scale LLM Training
Memetic Search for Green Vehicle Routing Problem with Private Capacitated Refueling Stations
From Automation to Autonomy in Smart Manufacturing: A Bayesian Optimization Framework for Modeling Multi-Objective Experimentation and Sequential Decision Making
Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning
Maya: Optimizing Deep Learning Training Workloads using Emulated Virtual Accelerators
FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs
KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies
CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning
Disentangling Uncertainties by Learning Compressed Data Representation
Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model
HyperArm Bandit Optimization: A Novel approach to Hyperparameter Optimization and an Analysis of Bandit Algorithms in Stochastic and Adversarial Settings
Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration
Reward-Centered ReST-MCTS: A Robust Decision-Making Framework for Robotic Manipulation in High Uncertainty Environments
Probabilistic Insights for Efficient Exploration Strategies in Reinforcement Learning
A Transformer Model for Predicting Chemical Reaction Products from Generic Templates
Contextualizing biological perturbation experiments through language
On Space-Filling Input Design for Nonlinear Dynamic Model Learning: A Gaussian Process Approach
Training a Generally Curious Agent
Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.