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 421–430 of 514 papers

TitleStatusHype
Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problemsCode0
Multirobot Coverage of Modular EnvironmentsCode0
Sparse Reward Exploration via Novelty Search and EmittersCode0
Count-Based Exploration in Feature Space for Reinforcement LearningCode0
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision ProcessesCode0
The split Gibbs sampler revisited: improvements to its algorithmic structure and augmented target distributionCode0
Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and GeneralizationCode0
Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic SystemsCode0
Neural Contextual Bandits with UCB-based ExplorationCode0
Dynamic Subgoal-based Exploration via Bayesian OptimizationCode0
Show:102550
← PrevPage 43 of 52Next →

No leaderboard results yet.