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
Approximate information for efficient exploration-exploitation strategies—0
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning—0
A Temporally Correlated Latent Exploration for Reinforcement Learning—0
A Transformer Model for Predicting Chemical Reaction Products from Generic Templates—0
A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search—0
Auto-MAP: A DQN Framework for Exploring Distributed Execution Plans for DNN Workloads—0
Autonomous synthesis of metastable materials—0
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation—0
A Web-scale system for scientific knowledge exploration—0
Bag of Policies for Distributional Deep Exploration—0
Show:102550
← PrevPage 35 of 52Next →

No leaderboard results yet.