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 351–360 of 514 papers

TitleStatusHype
Efficient Exploration for Model-based Reinforcement Learning with Continuous States and Actions—0
Novelty Search in Representational Space for Sample Efficient ExplorationCode1
SEMI: Self-supervised Exploration via Multisensory Incongruity—0
PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning—0
Occupancy Anticipation for Efficient Exploration and NavigationCode1
DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the LoopCode1
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement LearningCode1
Auto-MAP: A DQN Framework for Exploring Distributed Execution Plans for DNN Workloads—0
See, Hear, Explore: Curiosity via Audio-Visual AssociationCode1
Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic SystemsCode0
Show:102550
← PrevPage 36 of 52Next →

No leaderboard results yet.