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 331–340 of 514 papers

TitleStatusHype
Entropic Risk-Sensitive Reinforcement Learning: A Meta Regret Framework with Function Approximation—0
Intrinsically Guided Exploration in Meta Reinforcement Learning—0
Optimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning—0
Online Limited Memory Neural-Linear Bandits—0
MQES: Max-Q Entropy Search for Efficient Exploration in Continuous Reinforcement Learning—0
Robotic Grasping of Fully-Occluded Objects using RF Perception—0
Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning—0
BeBold: Exploration Beyond the Boundary of Explored RegionsCode1
SAR Image Despeckling Based on Convolutional Denoising Autoencoder—0
Hybrid Genetic Search for the CVRP: Open-Source Implementation and SWAP* NeighborhoodCode1
Show:102550
← PrevPage 34 of 52Next →

No leaderboard results yet.