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 201–250 of 514 papers

TitleStatusHype
Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution—0
Successor-Predecessor Intrinsic Exploration—0
Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models—0
Joint Falsification and Fidelity Settings Optimization for Validation of Safety-Critical Systems: A Theoretical Analysis—0
Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization—0
Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement LearningCode0
Fast exploration and learning of latent graphs with aliased observations—0
Exploration of the search space of Gaussian graphical models for paired data—0
Policy Mirror Descent Inherently Explores Action Space—0
Exploration via Epistemic Value Estimation—0
Guarded Policy Optimization with Imperfect Online Demonstrations—0
Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization—0
Efficient Informed Proposals for Discrete Distributions via Newton's Series Approximation—0
Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret—0
Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical RobotCode2
Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization—0
Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning—0
Computational Discovery of Microstructured Composites with Optimal Stiffness-Toughness Trade-Offs—0
GFlowNets for AI-Driven Scientific Discovery—0
ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation—0
Embodied Agents for Efficient Exploration and Smart Scene Description—0
Exploration in Model-based Reinforcement Learning with Randomized Reward—0
Strangeness-driven Exploration in Multi-Agent Reinforcement LearningCode0
SHIRO: Soft Hierarchical Reinforcement Learning—0
Generative Colorization of Structured Mobile Web PagesCode1
Reinforcement Learning in Credit Scoring and Underwriting—0
Efficient Exploration in Resource-Restricted Reinforcement Learning—0
Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning—0
CURO: Curriculum Learning for Relative Overgeneralization—0
HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression—0
Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions—0
CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control—0
Efficient Exploration using Model-Based Quality-Diversity with Gradients—0
Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation—0
Exploring through Random Curiosity with General Value FunctionsCode0
Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction—0
Design of Convolutional Extreme Learning Machines for Vision-Based Navigation Around Small Bodies—0
GeoThermalCloud: Machine Learning for Geothermal Resource ExplorationCode1
Deep Active Ensemble Sampling For Image Classification—0
LECO: Learnable Episodic Count for Task-Specific Intrinsic RewardCode0
The Role of Coverage in Online Reinforcement Learning—0
Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-GraspsCode1
Self-supervised Sequential Information Bottleneck for Robust Exploration in Deep Reinforcement Learning—0
Deterministic Sequencing of Exploration and Exploitation for Reinforcement Learning—0
An Empirical Evaluation of Posterior Sampling for Constrained Reinforcement LearningCode0
SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and PlanningCode1
Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and ExplorationsCode0
Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks—0
SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks—0
GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning—0
Show:102550
← PrevPage 5 of 11Next →

No leaderboard results yet.