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 501–514 of 514 papers

TitleStatusHype
Preference-Guided Reinforcement Learning for Efficient ExplorationCode0
Bayesian Reinforcement Learning via Deep, Sparse SamplingCode0
Principled Exploration via Optimistic Bootstrapping and Backward InductionCode0
Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted IlluminationCode0
Variational Deep Q NetworkCode0
Map Induction: Compositional spatial submap learning for efficient exploration in novel environmentsCode0
Mapping Galaxy Images Across Ultraviolet, Visible and Infrared Bands Using Generative Deep LearningCode0
Scheduled Policy Optimization for Natural Language Communication with Intelligent AgentsCode0
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement LearningCode0
Batch Bayesian Optimization via Local PenalizationCode0
Better Exploration with Optimistic Actor CriticCode0
Provably Efficient Exploration for Reinforcement Learning Using Unsupervised LearningCode0
Balancing Value Underestimation and Overestimation with Realistic Actor-CriticCode0
Curiosity Driven Exploration of Learned Disentangled Goal SpacesCode0
Show:102550
← PrevPage 11 of 11Next →

No leaderboard results yet.