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 241–250 of 514 papers

TitleStatusHype
Guided Exploration for Efficient Relational Model Learning—0
Hands-Free Segmentation of Medical Volumes via Binary Inputs—0
Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning—0
HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression—0
HelixDesign-Binder: A Scalable Production-Grade Platform for Binder Design Built on HelixFold3—0
KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance—0
Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path—0
Efficient Exploration in Binary and Preferential Bayesian Optimization—0
A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search—0
Aerial Active STAR-RIS-assisted Satellite-Terrestrial Covert Communications—0
Show:102550
← PrevPage 25 of 52Next →

No leaderboard results yet.