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 101–125 of 514 papers

TitleStatusHype
Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal GuidanceCode0
Bayesian Reinforcement Learning via Deep, Sparse SamplingCode0
Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and GeneralizationCode0
Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug DesignCode0
Balancing Value Underestimation and Overestimation with Realistic Actor-CriticCode0
GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal BabblingCode0
Count-Based Exploration with the Successor RepresentationCode0
Count-Based Exploration in Feature Space for Reinforcement LearningCode0
Behavior-Guided Actor-Critic: Improving Exploration via Learning Policy Behavior Representation for Deep Reinforcement LearningCode0
Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic SystemsCode0
A New Bandit Setting Balancing Information from State Evolution and Corrupted ContextCode0
Generalization and Exploration via Randomized Value FunctionsCode0
Personalized Algorithmic Recourse with Preference ElicitationCode0
GenPlan: Generative Sequence Models as Adaptive PlannersCode0
Few-shot_LLM_Synthetic_Data_with_Distribution_MatchingCode0
A Variational Approach to Bayesian Phylogenetic InferenceCode0
Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based GamesCode0
A Gradient Sampling Algorithm for Stratified Maps with Applications to Topological Data AnalysisCode0
Consensus-based adaptive sampling and approximation for high-dimensional energy landscapesCode0
Federated Control with Hierarchical Multi-Agent Deep Reinforcement LearningCode0
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement LearningCode0
Discovering and Exploiting Sparse Rewards in a Learned Behavior SpaceCode0
Adaptive teachers for amortized samplersCode0
Disentangling Uncertainties by Learning Compressed Data RepresentationCode0
ConEx: Efficient Exploration of Big-Data System Configurations for Better PerformanceCode0
Show:102550
← PrevPage 5 of 21Next →

No leaderboard results yet.