SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 501–514 of 514 papers

TitleStatusHype
Large-scale signatures of unconsciousness are consistent with a departure from critical dynamics—0
Batch Bayesian Optimization via Local PenalizationCode0
Bandit Algorithms for Tree Search—0
Stochastic Gradient Hamiltonian Monte CarloCode0
Safe Exploration of State and Action Spaces in Reinforcement Learning—0
Generalization and Exploration via Randomized Value FunctionsCode0
Sparse graphs using exchangeable random measures—0
Volumetric Spanners: an Efficient Exploration Basis for Learning—0
Efficient Exploration and Value Function Generalization in Deterministic Systems—0
Extended Formulations for Online Linear Bandit Optimization—0
The University of Cambridge Russian-English System at WMT13—0
Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization—0
(More) Efficient Reinforcement Learning via Posterior Sampling—0
A Community Based Algorithm for Large Scale Web Service Composition—0
Show:102550
← PrevPage 11 of 11Next →

No leaderboard results yet.