Active Exploration

Active exploration in reinforcement learning focuses on efficiently gathering information to improve decision-making in uncertain environments, aiming to balance exploration of unknown states with exploitation of current knowledge. Current research emphasizes developing algorithms that enhance exploration efficiency, often employing techniques like Bayesian optimization, Thompson sampling, and various deep reinforcement learning architectures (e.g., Proximal Policy Optimization, Twin Delayed Deep Deterministic Policy Gradient) to guide the exploration process. This research is significant for improving the sample efficiency of reinforcement learning agents across diverse applications, from robotics and autonomous navigation to scientific experimentation and personalized recommendations, ultimately leading to more robust and adaptable intelligent systems.

Papers

April 2, 2024

Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation
Carlos Plou, Ana C. Murillo, Ruben Martinez-Cantin
Reinforcement Learning Robotics Domain Robot Manipulation Active Exploration

December 22, 2023

Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration
Honghao Wei, Xin Liu, Lei Ying
Integral Role Safe Reinforcement Learning Linear Function Approximation Active Exploration

December 1, 2023

Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration
Viraj Mehta, Vikramjeet Das, Ojash Neopane, Yijia Dai, Ilija Bogunovic, Jeff Schneider, Willie Neiswanger
Reinforcement Learning Human Feedback Active Exploration Sample Efficient Reinforcement Learning Upper Confidence Bound Rate Optimal Regret

November 3, 2023

Active Reasoning in an Open-World Environment
Manjie Xu, Guangyuan Jiang, Wei Liang, Chi Zhang, Yixin Zhu
Open World Active Exploration Collaborative Reasoning

October 30, 2023

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Guowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé, Furong Huang, Huazhe Xu
Active Exploration Visual Reinforcement Learning Exploration Exploitation Trade Continuous Control Task

October 27, 2023

Improving Intrinsic Exploration by Creating Stationary Objectives
Roger Creus Castanyer, Joshua Romoff, Glen Berseth
Active Exploration Exploration Problem Time Varying Objective Intrinsic Exploration

October 26, 2023

Navigating to Success in Multi-Modal Human-Robot Collaboration: Analysis and Corpus Release
Stephanie M. Lukin, Kimberly A. Pollard, Claire Bonial, Taylor Hudson, Ron Arstein, Clare Voss, David Traum
General Analysis Human Robot Interaction Multi Modality Autonomous Exploration Active Exploration Financial Success Human Robot Communication

October 13, 2023

Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration
Fanqi Wan, Xinting Huang, Tao Yang, Xiaojun Quan, Wei Bi, Shuming Shi
Instruction Tuning Open Domain Tutorial Review Active Exploration Coverage Directed Test

October 1, 2023

BooookScore: A systematic exploration of book-length summarization in the era of LLMs
Yapei Chang, Kyle Lo, Tanya Goyal, Mohit Iyyer
Large Language Model New Era Summarization Task Active Exploration Long Document

September 18, 2023

Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach
Mohammad S. Ramadan, Mahmoud A. Hayajnh, Michael T. Tolley, Kyriakos G. Vamvoudakis
Reinforcement Learning Active Exploration Stochastic Optimal Control Stochastic Control Active Reinforcement Learning

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 13, 2023

Energy-Constrained Active Exploration Under Incremental-Resolution Symbolic Perception
Disha Kamale, Sofie Haesaert, Cristian-Ioan Vasile
Neuro Symbolic Autonomous Exploration Sequential Decision Making Problem Active Exploration Reward Maximization Mixed Integer Linear Programming

August 30, 2023

Cyclophobic Reinforcement Learning
Stefan Sylvius Wagner, Peter Arndt, Jan Robine, Stefan Harmeling
Reinforcement Learning Intrinsic Reward Active Exploration Curiosity Driven Exploration Reward Consistency

August 20, 2023

Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
Shintaro Nakamura, Masashi Sugiyama
Multi Armed Bandit Sample Complexity Thompson Sampling Active Exploration Combinatorial Pure Exploration

August 5, 2023

A Systematic Exploration of Joint-training for Singing Voice Synthesis
Yuning Wu, Yifeng Yu, Jiatong Shi, Tao Qian, Qin Jin
Speech Synthesis Acoustic Model Active Exploration Singing Voice Synthesis High Fidelity Vocoder Joint Training

July 27, 2023

Multi-Robot Multi-Room Exploration with Geometric Cue Extraction and Circular Decomposition
Seungchan Kim, Micah Corah, John Keller, Graeme Best, Sebastian Scherer
Multi Robot Aerial Robot Active Exploration Frontier Based Exploration Cue Point

July 20, 2023

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback
Marcel Torne, Max Balsells, Zihan Wang, Samedh Desai, Tao Chen, Pulkit Agrawal, Abhishek Gupta
Reinforcement Learning Human in the Loop Active Exploration Pseudo Goal Goal Conditioned Exploration Incentivized Exploration Uninformed Exploration

July 6, 2023

TDLE: 2-D LiDAR Exploration With Hierarchical Planning Using Regional Division
Xuyang Zhao, Chengpu Yu, Erpei Xu, Yixuan Liu
Environment Exploration Autonomous Exploration Region Specific Active Exploration Hierarchical Planning 2 Dimensional LiDAR

June 23, 2023

Active Coverage for PAC Reinforcement Learning
Aymen Al-Marjani, Andrea Tirinzoni, Emilie Kaufmann
Reinforcement Learning Active Exploration Episodic Markov Decision Process Reward Free Exploration Entity Coverage

June 21, 2023

Optimistic Active Exploration of Dynamical Systems
Bhavya Sukhija, Lenart Treven, Cansu Sancaktar, Sebastian Blaes, Stelian Coros, Andreas Krause
Zero Shot Dynamical System Active Exploration Unknown Dynamic

Active Exploration

Papers

Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation

Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration

Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration

Active Reasoning in an Open-World Environment

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Improving Intrinsic Exploration by Creating Stationary Objectives

Navigating to Success in Multi-Modal Human-Robot Collaboration: Analysis and Corpus Release

Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration

BooookScore: A systematic exploration of book-length summarization in the era of LLMs

Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach

DEUX: Active Exploration for Learning Unsupervised Depth Perception

Energy-Constrained Active Exploration Under Incremental-Resolution Symbolic Perception

Cyclophobic Reinforcement Learning

Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit

A Systematic Exploration of Joint-training for Singing Voice Synthesis

Multi-Robot Multi-Room Exploration with Geometric Cue Extraction and Circular Decomposition

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

TDLE: 2-D LiDAR Exploration With Hierarchical Planning Using Regional Division

Active Coverage for PAC Reinforcement Learning

Optimistic Active Exploration of Dynamical Systems