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 201–210 of 514 papers

TitleStatusHype
Directed Exploration for Reinforcement Learning—0
Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning—0
Diffusion Models Meet Contextual Bandits with Large Action Spaces—0
Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving—0
Beyond Games: Bringing Exploration to Robots in Real-world—0
Approximate information for efficient exploration-exploitation strategies—0
Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning—0
DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models—0
Differentially Evolving Memory Ensembles: Pareto Optimization based on Computational Intelligence for Embedded Memories on a System Level—0
Better Exploration with Optimistic Actor-Critic—0
Show:102550
← PrevPage 21 of 52Next →

No leaderboard results yet.