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 451–460 of 514 papers

TitleStatusHype
NSGA-Net: Neural Architecture Search using Multi-Objective Genetic AlgorithmCode0
On Preemption and Learning in Stochastic SchedulingCode0
ConEx: Efficient Exploration of Big-Data System Configurations for Better PerformanceCode0
Stochastic Gradient Hamiltonian Monte CarloCode0
Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank BanditsCode0
Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement LearningCode0
Robust quantum dots charge autotuning using neural network uncertaintyCode0
Strangeness-driven Exploration in Multi-Agent Reinforcement LearningCode0
Online Limited Memory Neural-Linear Bandits with Likelihood MatchingCode0
On Machine Learning-Driven Surrogates for Sound Transmission Loss SimulationsCode0
Show:102550
← PrevPage 46 of 52Next →

No leaderboard results yet.