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 51–60 of 514 papers

TitleStatusHype
Mapping Galaxy Images Across Ultraviolet, Visible and Infrared Bands Using Generative Deep LearningCode0
Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science—0
Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability GraphsCode0
ActiveGAMER: Active GAussian Mapping through Efficient Rendering—0
β-DQN: Improving Deep Q-Learning By Evolving the Behavior—0
Provably Efficient Exploration in Reward Machines with Low Regret—0
A diversity-enhanced genetic algorithm for efficient exploration of parameter spacesCode0
GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering—0
GenPlan: Generative Sequence Models as Adaptive PlannersCode0
A Temporally Correlated Latent Exploration for Reinforcement Learning—0
Show:102550
← PrevPage 6 of 52Next →

No leaderboard results yet.