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 351–360 of 514 papers

TitleStatusHype
Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion—0
Guarded Policy Optimization with Imperfect Online Demonstrations—0
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
Hierarchical reinforcement learning for efficient exploration and transfer—0
HyperArm Bandit Optimization: A Novel approach to Hyperparameter Optimization and an Analysis of Bandit Algorithms in Stochastic and Adversarial Settings—0
Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning—0
Show:102550
← PrevPage 36 of 52Next →

No leaderboard results yet.