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 171–180 of 514 papers

TitleStatusHype
Information Content Exploration—0
Learning Optimal Power Flow Value Functions with Input-Convex Neural Networks—0
PGDQN: Preference-Guided Deep Q-NetworkCode1
Feature Interaction Aware Automated Data Representation TransformationCode0
DREAM: Decentralized Reinforcement Learning for Exploration and Efficient Energy Management in Multi-Robot Systems—0
Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need—0
Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug DesignCode0
Learning Spatial and Temporal Hierarchies: Hierarchical Active Inference for navigation in Multi-Room Maze Environments—0
Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects—0
Go Beyond Imagination: Maximizing Episodic Reachability with World ModelsCode0
Show:102550
← PrevPage 18 of 52Next →

No leaderboard results yet.