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 191–200 of 514 papers

TitleStatusHype
Bayesian Curiosity for Efficient Exploration in Reinforcement LearningCode0
Principled Exploration via Optimistic Bootstrapping and Backward InductionCode0
Distributional Perturbation for Efficient Exploration in Distributional Reinforcement Learning—0
Distilling Realizable Students from Unrealizable Teachers—0
Discovering Context Specific Causal Relationships—0
BooVI: Provably Efficient Bootstrapped Value Iteration—0
DISCO-10M: A Large-Scale Music Dataset—0
Directed Exploration in PAC Model-Free Reinforcement Learning—0
Biased Estimates of Advantages over Path Ensembles—0
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning—0
Show:102550
← PrevPage 20 of 52Next →

No leaderboard results yet.