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 261–270 of 514 papers

TitleStatusHype
Strangeness-driven Exploration in Multi-Agent Reinforcement LearningCode0
SHIRO: Soft Hierarchical Reinforcement Learning—0
Reinforcement Learning in Credit Scoring and Underwriting—0
Efficient Exploration in Resource-Restricted Reinforcement Learning—0
Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning—0
CURO: Curriculum Learning for Relative Overgeneralization—0
HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression—0
Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions—0
CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control—0
Efficient Exploration using Model-Based Quality-Diversity with Gradients—0
Show:102550
← PrevPage 27 of 52Next →

No leaderboard results yet.