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 41–50 of 514 papers

TitleStatusHype
Landmark-Guided Subgoal Generation in Hierarchical Reinforcement LearningCode1
Contextualizing biological perturbation experiments through languageCode1
A Langevin-like Sampler for Discrete DistributionsCode1
Layered and Staged Monte Carlo Tree Search for SMT Strategy SynthesisCode1
Learning Exploration Policies for NavigationCode1
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct SolutionsCode1
A Survey of Label-Efficient Deep Learning for 3D Point CloudsCode1
Deep Bandits Show-Off: Simple and Efficient Exploration with Deep NetworksCode1
A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?Code1
Episodic Multi-agent Reinforcement Learning with Curiosity-Driven ExplorationCode1
Show:102550
← PrevPage 5 of 52Next →

No leaderboard results yet.