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 381–390 of 514 papers

TitleStatusHype
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation—0
CURO: Curriculum Learning for Relative Overgeneralization—0
Data-Efficient Exploration with Self Play for Atari—0
Deep Active Ensemble Sampling For Image Classification—0
Deep density networks and uncertainty in recommender systems—0
Deep exploration by novelty-pursuit with maximum state entropy—0
Deep Exploration via Randomized Value Functions—0
DEEPGONET: Multi-label Prediction of GO Annotation for Protein from Sequence Using Cascaded Convolutional and Recurrent Network—0
Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching—0
Design of Convolutional Extreme Learning Machines for Vision-Based Navigation Around Small Bodies—0
Show:102550
← PrevPage 39 of 52Next →

No leaderboard results yet.