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.
A Web-scale system for scientific knowledge exploration
When Simple Exploration is Sample Efficient: Identifying Sufficient Conditions for Random Exploration to Yield PAC RL Algorithms
Efficient Exploration of Gradient Space for Online Learning to Rank
Exploration by Distributional Reinforcement Learning
A Human Mixed Strategy Approach to Deep Reinforcement Learning
Variance Networks: When Expectation Does Not Meet Your Expectations
Dimension-Robust MCMC in Bayesian Inverse Problems
Efficient Exploration through Bayesian Deep Q-Networks
Diversity-Driven Exploration Strategy for Deep Reinforcement Learning
Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning
Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning
The Eigenoption-Critic Framework
Reinforced dynamics for enhanced sampling in large atomic and molecular systems
Noisy Natural Gradient as Variational Inference
Variational Deep Q Network
Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation
Efficient exploration with Double Uncertain Value Networks
A Compression-Inspired Framework for Macro Discovery
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
Deep density networks and uncertainty in recommender systems
Vector Quantization using the Improved Differential Evolution Algorithm for Image Compression
Feature Engineering for Predictive Modeling using Reinforcement Learning
Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning
Protein design by multiobjective optimization: evolutionary and non-evolutionary approaches
Noisy Networks for Exploration
Count-Based Exploration in Feature Space for Reinforcement Learning
Fractional Langevin Monte Carlo: Exploring Lévy Driven Stochastic Differential Equations for Markov Chain Monte Carlo
K-Means Clustering using Tabu Search with Quantized Means
Deep Exploration via Randomized Value Functions
Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted Illumination
Efficient Pose and Cell Segmentation using Column Generation
Contextual Decision Processes with Low Bellman Rank are PAC-Learnable
Automatic chemical design using a data-driven continuous representation of molecules
Hands-Free Segmentation of Medical Volumes via Binary Inputs
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.