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 341–350 of 514 papers

TitleStatusHype
Efficient Optimal Selection for Composited Advertising Creatives with Tree StructureCode0
Learning Memory-Dependent Continuous Control from Demonstrations—0
Meta-Thompson Sampling—0
Online Limited Memory Neural-Linear Bandits with Likelihood MatchingCode0
Sparse Reward Exploration via Novelty Search and EmittersCode0
The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors—0
Autonomous synthesis of metastable materials—0
Optimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning—0
Entropic Risk-Sensitive Reinforcement Learning: A Meta Regret Framework with Function Approximation—0
MQES: Max-Q Entropy Search for Efficient Exploration in Continuous Reinforcement Learning—0
Show:102550
← PrevPage 35 of 52Next →

No leaderboard results yet.