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 431–440 of 514 papers

TitleStatusHype
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context VariablesCode0
Concurrent Meta Reinforcement LearningCode0
Bayesian Reinforcement Learning via Deep, Sparse SamplingCode0
Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching—0
Information-Directed Exploration for Deep Reinforcement LearningCode0
Exploration Bonus for Regret Minimization in Undiscounted Discrete and Continuous Markov Decision Processes—0
Playing Text-Adventure Games with Graph-Based Deep Reinforcement LearningCode0
Context-Dependent Upper-Confidence Bounds for Directed Exploration—0
Incentivizing Exploration with Selective Data Disclosure—0
DEEPGONET: Multi-label Prediction of GO Annotation for Protein from Sequence Using Cascaded Convolutional and Recurrent Network—0
Show:102550
← PrevPage 44 of 52Next →

No leaderboard results yet.