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 1–50 of 514 papers

TitleStatusHype
Cradle: Empowering Foundation Agents Towards General Computer ControlCode7
Streamlining Ocean Dynamics Modeling with Fourier Neural Operators: A Multiobjective Hyperparameter and Architecture Optimization ApproachCode7
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical ReasoningCode5
Iterated Denoising Energy Matching for Sampling from Boltzmann DensitiesCode2
GenNBV: Generalizable Next-Best-View Policy for Active 3D ReconstructionCode2
MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary ProgrammingCode2
Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical RobotCode2
ForesightNav: Learning Scene Imagination for Efficient ExplorationCode2
Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language NavigationCode2
Online Decision TransformerCode2
LtU-ILI: An All-in-One Framework for Implicit Inference in Astrophysics and CosmologyCode2
Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction FollowingCode2
Occupancy Anticipation for Efficient Exploration and NavigationCode1
Meta Reinforcement Learning with Autonomous Inference of Subtask DependenciesCode1
Navigating Chemical Space with Latent FlowsCode1
Maximum Entropy Reinforcement Learning with Diffusion PolicyCode1
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct SolutionsCode1
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven ExplorationCode1
Optimistic Exploration even with a Pessimistic InitialisationCode1
Latent World Models For Intrinsically Motivated ExplorationCode1
Landmark-Guided Subgoal Generation in Hierarchical Reinforcement LearningCode1
Layered and Staged Monte Carlo Tree Search for SMT Strategy SynthesisCode1
Learning to Solve Combinatorial Graph Partitioning Problems via Efficient ExplorationCode1
Leveraging Skills from Unlabeled Prior Data for Efficient Online ExplorationCode1
MADE: Exploration via Maximizing Deviation from Explored RegionsCode1
MAMBA: an Effective World Model Approach for Meta-Reinforcement LearningCode1
HyperDQN: A Randomized Exploration Method for Deep Reinforcement LearningCode1
Model-Based Active ExplorationCode1
NovelD: A Simple yet Effective Exploration CriterionCode1
Novelty Search in Representational Space for Sample Efficient ExplorationCode1
GNN-DT: Graph Neural Network Enhanced Decision Transformer for Efficient Optimization in Dynamic EnvironmentsCode1
SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and PlanningCode1
Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-GraspsCode1
Automatic chemical design using a data-driven continuous representation of moleculesCode1
Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid LocomotionCode1
Diffusion-Reinforcement Learning Hierarchical Motion Planning in Multi-agent Adversarial GamesCode1
Episodic Multi-agent Reinforcement Learning with Curiosity-Driven ExplorationCode1
Evolutionary Large Language Model for Automated Feature TransformationCode1
Deep Bandits Show-Off: Simple and Efficient Exploration with Deep NetworksCode1
GeoThermalCloud: Machine Learning for Geothermal Resource ExplorationCode1
Hierarchical Skills for Efficient ExplorationCode1
Hybrid Genetic Search for the CVRP: Open-Source Implementation and SWAP* NeighborhoodCode1
A Langevin-like Sampler for Discrete DistributionsCode1
Adversarially Guided Actor-CriticCode1
BeBold: Exploration Beyond the Boundary of Explored RegionsCode1
Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic LearningCode1
DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the LoopCode1
A Survey of Label-Efficient Deep Learning for 3D Point CloudsCode1
A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?Code1
Contextualizing biological perturbation experiments through languageCode1
Show:102550
← PrevPage 1 of 11Next →

No leaderboard results yet.