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 361–370 of 514 papers

TitleStatusHype
End-Effect Exploration Drive for Effective Motor Learning—0
Task-agnostic Exploration in Reinforcement Learning—0
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven ExplorationCode1
Shared Experience Actor-Critic for Multi-Agent Reinforcement LearningCode1
From proprioception to long-horizon planning in novel environments: A hierarchical RL model—0
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient ExplorationCode0
Multirobot Coverage of Modular EnvironmentsCode0
PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning—0
Weakly-Supervised Reinforcement Learning for Controllable Behavior—0
Bayesian optimisation of large-scale photonic reservoir computers—0
Show:102550
← PrevPage 37 of 52Next →

No leaderboard results yet.