Uncertainty Aware Exploration

Uncertainty-aware exploration aims to improve decision-making in various fields by intelligently managing uncertainty during the exploration phase. Current research focuses on developing algorithms that effectively combine epistemic (knowledge-based) and aleatory (inherent randomness) uncertainty, often employing Bayesian methods, distributional reinforcement learning, or Gaussian processes within model-based or hybrid approaches. This research is significant because it enhances the efficiency and robustness of learning processes in complex environments, impacting fields like robotics, recommendation systems, and inverse problem solving by enabling more reliable and sample-efficient solutions.

Papers

October 16, 2024

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning
Ng Wen Zheng Terence, Chen Jianda
Reinforcement Learning Domain Adaptation Sim to Real Reinforcement Learning Robust Agent Uncertainty Aware Exploration

July 22, 2024

Deep Uncertainty-Based Explore for Index Construction and Retrieval in Recommendation System
Xin Jiang, Kaiqiang Wang, Yinlong Wang, Fengchang Lv, Taiyang Peng, Shuai Yang, Xianteng Wu, Pengye Zhang, Shuo Yuan, Yifan Zeng
App to App Retrieval Recommendation System Recommendation Quality Uncertainty Aware Exploration Uncertainty Score Deep Matching Index Structure

May 24, 2024

Hierarchical Uncertainty Exploration via Feedforward Posterior Trees
Elias Nehme, Rotem Mulayoff, Tomer Michaeli
Posterior Inference Ill Posed Inverse Problem Diffusion Posterior Sampling Uncertainty Aware Exploration Consistent Reconstruction Image Restoration Problem

January 5, 2024

A unified uncertainty-aware exploration: Combining epistemic and aleatory uncertainty
Parvin Malekzadeh, Ming Hou, Konstantinos N. Plataniotis
Epistemic Uncertainty Aleatoric Uncertainty Uncertainty Aware Exploration

November 22, 2023

Risk-sensitive Markov Decision Process and Learning under General Utility Functions
Zhengqi Wu, Renyuan Xu
Reinforcement Learning LeArning Abstract Markov Decision Process Near Optimal Policy Risk Sensitive Reinforcement Learning Utility Function Uncertainty Aware Exploration

November 19, 2023

What Lies beyond the Pareto Front? A Survey on Decision-Support Methods for Multi-Objective Optimization
Zuzanna Osika, Jazmin Zatarain Salazar, Diederik M. Roijers, Frans A. Oliehoek, Pradeep K. Murukannaiah
Timely Survey Decision Making Multi Objective Optimization Pareto Front Multiobjective Optimization Uncertainty Aware Exploration

October 16, 2023

Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning
Parvin Malekzadeh, Ming Hou, Konstantinos N. Plataniotis
Knowledge Transfer New Task Successor Representation Uncertainty Aware Exploration

September 21, 2023

Uncertainty-driven Exploration Strategies for Online Grasp Learning
Yitian Shi, Philipp Schillinger, Miroslav Gabriel, Alexander Qualmann, Zohar Feldman, Hanna Ziesche, Ngo Anh Vien
Grasp Learning Grasp Prediction Uncertainty Aware Exploration

September 16, 2023

DEUX: Active Exploration for Learning Unsupervised Depth Perception
Marvin Chancán, Alex Wong, Ian Abraham
Depth Completion Active Exploration Depth Estimation Model Uncertainty Aware Exploration Depth Completion Model Unsupervised Depth Estimation Unsupervised Depth Completion

September 11, 2023

CARE: Confidence-rich Autonomous Robot Exploration using Bayesian Kernel Inference and Optimization
Yang Xu, Ronghao Zheng, Senlin Zhang, Meiqin Liu, Shoudong Huang
Optimization Purpose Bayesian Optimization CaRE SD Exploration Performance Bayesian Kernel Uncertainty Aware Exploration

May 16, 2023

Sorting and Hypergraph Orientation under Uncertainty with Predictions
Thomas Erlebach, Murilo Santos de Lima, Nicole Megow, Jens Schlöter
Human Prediction High Uncertainty Anticipation Worst Case Auxiliary Sorting Network Rearranges Learning Augmented Algorithm Veracity Prediction Input Uncertainty Uncertainty Aware Exploration

December 13, 2022

PPO-UE: Proximal Policy Optimization via Uncertainty-Aware Exploration
Qisheng Zhang, Zhen Guo, Audun Jøsang, Lance M. Kaplan, Feng Chen, Dong H. Jeong, Jin-Hee Cho
Proximal Policy Optimization Policy Optimization Active Exploration Uncertainty Aware Exploration

August 22, 2022

Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics
Jun Jet Tai, Jordan K. Terry, Mauro S. Innocente, James Brusey, Nadjim Horri
Reinforcement Learning Reinforcement Learning Benchmark Sparse Reward Environment Test Oracle Actor Critic Reinforcement Learning Epistemic Uncertainty Quantification Uncertainty Aware Exploration

Uncertainty Aware Exploration

Papers

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning

Deep Uncertainty-Based Explore for Index Construction and Retrieval in Recommendation System

Hierarchical Uncertainty Exploration via Feedforward Posterior Trees

A unified uncertainty-aware exploration: Combining epistemic and aleatory uncertainty

Risk-sensitive Markov Decision Process and Learning under General Utility Functions

What Lies beyond the Pareto Front? A Survey on Decision-Support Methods for Multi-Objective Optimization

Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning

Uncertainty-driven Exploration Strategies for Online Grasp Learning

DEUX: Active Exploration for Learning Unsupervised Depth Perception

CARE: Confidence-rich Autonomous Robot Exploration using Bayesian Kernel Inference and Optimization

Sorting and Hypergraph Orientation under Uncertainty with Predictions

PPO-UE: Proximal Policy Optimization via Uncertainty-Aware Exploration

Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics