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 476–500 of 514 papers

TitleStatusHype
Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation—0
Variational Deep Q NetworkCode0
Efficient exploration with Double Uncertain Value Networks—0
A Compression-Inspired Framework for Macro Discovery—0
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems—0
Deep density networks and uncertainty in recommender systems—0
Vector Quantization using the Improved Differential Evolution Algorithm for Image Compression—0
Feature Engineering for Predictive Modeling using Reinforcement Learning—0
Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for MCMC—0
Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning—0
Protein design by multiobjective optimization: evolutionary and non-evolutionary approaches—0
Life-iNet: A Structured Network-Based Knowledge Exploration and Analytics System for Life Sciences—0
Noisy Networks for ExplorationCode0
Count-Based Exploration in Feature Space for Reinforcement LearningCode0
Fractional Langevin Monte Carlo: Exploring Lévy Driven Stochastic Differential Equations for Markov Chain Monte Carlo—0
K-Means Clustering using Tabu Search with Quantized Means—0
Deep Exploration via Randomized Value Functions—0
Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted IlluminationCode0
Efficient Pose and Cell Segmentation using Column Generation—0
Contextual Decision Processes with Low Bellman Rank are PAC-Learnable—0
Hands-Free Segmentation of Medical Volumes via Binary Inputs—0
Processing Document Collections to Automatically Extract Linked Data: Semantic Storytelling Technologies for Smart Curation Workflows—0
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems—0
Deep Exploration via Bootstrapped DQNCode0
Angrier Birds: Bayesian reinforcement learningCode0
Show:102550
← PrevPage 20 of 21Next →

No leaderboard results yet.