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.
DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models
FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matching
Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts
Maximum Entropy Reinforcement Learning with Diffusion Policy
Massively Scaling Explicit Policy-conditioned Value Functions
Causal Information Prioritization for Efficient Reinforcement Learning
Exploratory Diffusion Model for Unsupervised Reinforcement Learning
Guided Exploration for Efficient Relational Model Learning
Few-shot_LLM_Synthetic_Data_with_Distribution_Matching
Adaptive Exploration for Multi-Reward Multi-Policy Evaluation
GNN-DT: Graph Neural Network Enhanced Decision Transformer for Efficient Optimization in Dynamic Environments
Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
Constrained Hybrid Metaheuristic Algorithm for Probabilistic Neural Networks Learning
Mapping Galaxy Images Across Ultraviolet, Visible and Infrared Bands Using Generative Deep Learning
Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science
Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability Graphs
ActiveGAMER: Active GAussian Mapping through Efficient Rendering
$β$-DQN: Improving Deep Q-Learning By Evolving the Behavior
Provably Efficient Exploration in Reward Machines with Low Regret
A diversity-enhanced genetic algorithm for efficient exploration of parameter spaces
GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering
GenPlan: Generative Sequence Models as Adaptive Planners
A Temporally Correlated Latent Exploration for Reinforcement Learning
Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning
Sample Efficient Robot Learning in Supervised Effect Prediction Tasks
CBOL-Tuner: Classifier-pruned Bayesian optimization to explore temporally structured latent spaces for particle accelerator tuning
Adaptformer: Sequence models as adaptive iterative planners
Randomized-Grid Search for Hyperparameter Tuning in Decision Tree Model to Improve Performance of Cardiovascular Disease Classification
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problems
Learning Dynamic Cognitive Map with Autonomous Navigation
Scalable Sampling for High Utility Patterns
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
EfficientEQA: An Efficient Approach for Open Vocabulary Embodied Question Answering
Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.