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 71–80 of 514 papers

TitleStatusHype
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL—0
Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration—0
Leveraging Skills from Unlabeled Prior Data for Efficient Online ExplorationCode1
Scattered Forest Search: Smarter Code Space Exploration with LLMs—0
ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning—0
TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement LearningCode0
Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task ComplexityCode0
Latent Action Priors for Locomotion with Deep Reinforcement Learning—0
BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale—0
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical ReasoningCode5
Show:102550
← PrevPage 8 of 52Next →

No leaderboard results yet.