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 381–390 of 514 papers

TitleStatusHype
Latent Action Priors for Locomotion with Deep Reinforcement Learning—0
Learn2Hop: Learned Optimization on Rough Landscapes—0
Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks—0
Learning Causal Overhypotheses through Exploration in Children and Computational Models—0
Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy—0
Efficient Exploration via First-Person Behavior Cloning Assisted Rapidly-Exploring Random Trees—0
Learning Exploration Policies for Model-Agnostic Meta-Reinforcement Learning—0
Learning Index Selection with Structured Action Spaces—0
Learning Memory-Dependent Continuous Control from Demonstrations—0
Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration—0
Show:102550
← PrevPage 39 of 52Next →

No leaderboard results yet.