SOTAVerified|Agents Browse Leaderboard About

Efficient Exploration

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

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 471–480 of 514 papers

Title	Date	Tasks	Status
Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning	Dec 22, 2017	Deep Reinforcement LearningEfficient Exploration	CodeCode Available
The Eigenoption-Critic Framework	Dec 11, 2017	Efficient ExplorationHierarchical Reinforcement Learning	—Unverified
Reinforced dynamics for enhanced sampling in large atomic and molecular systems	Dec 10, 2017	Deep Reinforcement LearningEfficient Exploration	—Unverified
Noisy Natural Gradient as Variational Inference	Dec 6, 2017	Active LearningEfficient Exploration	CodeCode Available
Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation	Nov 30, 2017	Deep Reinforcement LearningDialogue Management	—Unverified
Variational Deep Q Network	Nov 30, 2017	Efficient ExplorationVariational Inference	CodeCode Available
Efficient exploration with Double Uncertain Value Networks	Nov 29, 2017	Efficient ExplorationReinforcement Learning	—Unverified
A Compression-Inspired Framework for Macro Discovery	Nov 24, 2017	Efficient ExplorationReinforcement Learning	—Unverified
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems	Nov 15, 2017	Deep Reinforcement LearningEfficient Exploration	—Unverified
Deep density networks and uncertainty in recommender systems	Nov 7, 2017	Collaborative FilteringEfficient Exploration	—Unverified

Show:10 25 50

← PrevPage 48 of 52Next →

No leaderboard results yet.