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 326–350 of 514 papers

TitleStatusHype
Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives—0
ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization—0
A Community Based Algorithm for Large Scale Web Service Composition—0
A Compression-Inspired Framework for Macro Discovery—0
Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation—0
ActiveGAMER: Active GAussian Mapping through Efficient Rendering—0
Active Model Estimation in Markov Decision Processes—0
ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning—0
Adaptformer: Sequence models as adaptive iterative planners—0
Adaptive Exploration for Multi-Reward Multi-Policy Evaluation—0
Aerial Active STAR-RIS-assisted Satellite-Terrestrial Covert Communications—0
A Human Mixed Strategy Approach to Deep Reinforcement Learning—0
A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage—0
An Explainable Nature-Inspired Framework for Monkeypox Diagnosis: Xception Features Combined with NGBoost and African Vultures Optimization Algorithm—0
An Offline Reinforcement Learning Algorithm Customized for Multi-Task Fusion in Large-Scale Recommender Systems—0
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 14 of 21Next →

No leaderboard results yet.