Random Exploration

Random exploration in artificial intelligence focuses on developing efficient strategies for agents to discover and learn about unknown environments or complex tasks, particularly in scenarios with sparse rewards or high dimensionality. Current research emphasizes the development of provably efficient algorithms, such as those based on Thompson sampling and optimistic sampling, often within frameworks like Bayesian optimization and multi-agent reinforcement learning, and incorporating techniques like perturbed-history exploration and ensemble value functions to improve exploration efficiency. These advancements are significant for improving the sample efficiency and robustness of reinforcement learning algorithms, with applications ranging from robotics and autonomous systems to resource management and personalized medicine.

Papers

October 31, 2024

Deterministic Exploration via Stationary Bellman Error Maximization
Sebastian Griesbach, Carlo D'Eramo
Reinforcement Learning Environment Exploration Intrinsic Reward Exploration Policy Bellman Error Random Exploration

September 17, 2024

Multi-UAV Uniform Sweep Coverage in Unknown Environments: A Mergeable Nervous System (MNS)-Based Random Exploration
Aryo Jamshidpey, Hugh H.-T. Liu
Unknown Environment Robot Swarm UAV Swarm Heterogeneous Swarm Random Exploration

May 30, 2024

Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation
Wooseong Cho, Taehyun Hwang, Joongkyu Lee, Min-hwan Oh
Reinforcement Learning Markov Decision Process Multinomial Logistic Random Exploration Frequentist Regret

April 16, 2024

Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning
Hao-Lun Hsu, Weixin Wang, Miroslav Pajic, Pan Xu
Cooperative Multi Agent Reinforcement Learning Random Exploration

January 30, 2024

Bayesian Optimization with Noise-Free Observations: Improved Regret Bounds via Random Exploration
Hwanwoo Kim, Daniel Sanz-Alonso
Bayesian Optimization Regret Bound Noisy Data UCB Algorithm New Algorithm Random Exploration

October 23, 2023

Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency
Sudeep Salgia, Sattar Vakili, Qing Zhao
Bayesian Optimization Computational Efficiency Order Optimal Regret Kernel Bandit Random Exploration

August 9, 2023

Frugal random exploration strategy for shape recognition using statistical geometry
Samuel Hidalgo-Caballero, Alvaro Cassinelli, Emmanuel Fort, Matthieu Labousse
Robotics Domain Robot Action Invariant Feature Robot Programming Shape Recognition Random Exploration Stochastic Geometry

June 26, 2023

Maximum State Entropy Exploration using Predecessor and Successor Representations
Arnav Kumar Jain, Lucas Lehnert, Irina Rish, Glen Berseth
Successor Representation Exploration Policy Reliable Learning Exploration Algorithm Random Exploration Entropy Exploration Novel Predecessor and Successor

May 15, 2023

Algorithmic Censoring in Dynamic Learning Systems
Jennifer Chien, Margaret Roberts, Berk Ustun
Training Data Dynamic Learning Random Exploration False Negative Prediction Selective Labeling

February 7, 2023

Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning
Lukas Schäfer, Oliver Slumbers, Stephen McAleer, Yali Du, Stefano V. Albrecht, David Mguni
Multi Agent Reinforcement Learning Multi Agent Efficient Exploration Multi Agent Exploration Random Exploration

January 13, 2023

Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm
Marc Höftmann, Jan Robine, Stefan Harmeling
State Representation Random Exploration Go Explore Myopic Exploration

October 13, 2022

Causality-driven Hierarchical Structure Discovery for Reinforcement Learning
Shaohui Peng, Xing Hu, Rui Zhang, Ke Tang, Jiaming Guo, Qi Yi, Ruizhi Chen, Xishan Zhang, Zidong Du, Ling Li, Qi Guo, Yunji Chen
Reinforcement Learning Causal Discovery Hierarchical Reinforcement Learning Random Exploration

July 30, 2022

Reinforcement learning with experience replay and adaptation of action dispersion
Paweł Wawrzyński, Wojciech Masarczyk, Mateusz Ostaszewski
Reinforcement Learning Adaptation Concern Black Box Optimization Experience Replay Effective Reinforcement Learning Random Exploration Action Distribution

Random Exploration

Papers

Deterministic Exploration via Stationary Bellman Error Maximization

Multi-UAV Uniform Sweep Coverage in Unknown Environments: A Mergeable Nervous System (MNS)-Based Random Exploration

Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation

Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning

Bayesian Optimization with Noise-Free Observations: Improved Regret Bounds via Random Exploration

Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency

Frugal random exploration strategy for shape recognition using statistical geometry

Maximum State Entropy Exploration using Predecessor and Successor Representations

Algorithmic Censoring in Dynamic Learning Systems

Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning

Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm

Causality-driven Hierarchical Structure Discovery for Reinforcement Learning

Reinforcement learning with experience replay and adaptation of action dispersion