Exploration Problem

The exploration problem in artificial intelligence focuses on enabling agents to efficiently discover and navigate unknown environments, maximizing coverage and finding optimal solutions in the face of uncertainty and sparse rewards. Current research emphasizes developing algorithms that combine the power of large language models and reinforcement learning, such as Go-Explore variants and novel methods incorporating intrinsic motivation and curriculum learning, to improve exploration efficiency and robustness in complex scenarios. These advancements are crucial for improving the capabilities of autonomous robots, optimizing resource allocation in large-scale systems, and accelerating progress in areas like reinforcement learning and multi-agent systems.

Papers

May 24, 2024

Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
Cong Lu, Shengran Hu, Jeff Clune
Exploration Problem Shoulder Joint Go Explore

May 12, 2024

Challenges and Opportunities for Large-Scale Exploration with Air-Ground Teams using Semantics
Fernando Cladera, Ian D. Miller, Zachary Ravichandran, Varun Murali, Jason Hughes, M. Ani Hsieh, C. J. Taylor, Vijay Kumar
Technical Challenge Non Humanoid Robot Emerging Opportunity Semantics Surfaced Unstructured Environment Ground Robot Exploration Problem Large Scale Exploration

March 12, 2024

Ariadne and Theseus: Exploration and Rendezvous with Two Mobile Agents in an Unknown Graph
Romain Cosson
Environment Exploration Rendezvous Problem Mobile Agent Exploration Problem Collaborative Exploration Unseen Graph Graph Exploration

February 5, 2024

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
Yingru Li, Jiawei Xu, Lei Han, Zhi-Quan Luo
Reinforcement Learning Practice Mode Bridging Text Exploration Problem Action Value Function

December 29, 2023

State Machine of Thoughts: Leveraging Past Reasoning Trajectories for Enhancing Problem Solving
Jia Liu, Jie Shuai, Xiyao Li
Thought Reasoning Problem Solving Model Based Agent Exploration Problem State Machine Reasoning Trajectory

December 27, 2023

Adaptive trajectory-constrained exploration strategy for deep reinforcement learning
Guojian Wang, Faguo Wu, Xiao Zhang, Ning Guo, Zhiming Zheng
Deep Reinforcement Learning Multi Agent Reinforcement Learning Adaptive Importance Exploration Problem Trajectory Wise Reward Adaptive Exploration Constrained Exploration

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

July 5, 2023

First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
Ben Norman, Jeff Clune
Exploration Problem Exploration Policy Exploration Strategy Intelligent Exploration

May 1, 2023

Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition
Yash Chandak, Shantanu Thakoor, Zhaohan Daniel Guo, Yunhao Tang, Remi Munos, Will Dabney, Diana L Borsa
Deep Reinforcement Learning Representation Learning Meaningful Representation Environment Exploration Singular Value Decomposition Deep Reinforcement Learning Agent Exploration Problem Predictive State Representation

January 27, 2023

Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation
Daesol Cho, Seungjae Lee, H. Jin Kim
Reinforcement Learning High Uncertainty Anticipation Temporal Information Exploration Problem Aware Curriculum Current Reinforcement Learning

January 19, 2023

Multi-Agent Interplay in a Competitive Survival Environment
Andrea Fanti
Multi Agent Emergent Behavior Multi Agent Interaction Exploration Problem Competitive Environment

November 24, 2022

Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems
Felix Chalumeau, Thomas Pierrot, Valentin Macé, Arthur Flajolet, Karim Beguir, Antoine Cully, Nicolas Perrin-Gilbert
Reinforcement Learning Evolutionary Algorithm Quality Diversity Exploration Problem Adaptive Robot

October 14, 2022

E2R: a Hierarchical-Learning inspired Novelty-Search method to generate diverse repertoires of grasping trajectories
Johann Huber, Oumar Sane, Alex Coninx, Faiz Ben Amar, Stephane Doncieux
Robotic Grasping Handwritten Trajectory Novelty Search Exploration Problem Robot Gripper

September 26, 2022

Delayed Geometric Discounts: An Alternative Criterion for Reinforcement Learning
Firas Jarboui, Ahmed Akakzia
Reinforcement Learning Optimal Behavior Exploration Problem Exponential Discounting

August 31, 2022

Cell-Free Latent Go-Explore
Quentin Gallouédec, Emmanuel Dellandréa
Reinforcement Learning Exploration Problem Go Explore Latent Exploration

June 16, 2022

BYOL-Explore: Exploration by Bootstrapped Prediction
Zhaohan Daniel Guo, Shantanu Thakoor, Miruna Pîslar, Bernardo Avila Pires, Florent Altché, Corentin Tallec, Alaa Saade, Daniele Calandriello, Jean-Bastien Grill, Yunhao Tang, Michal Valko, Rémi Munos, Mohammad Gheshlaghi Azar, Bilal Piot
Environment Exploration 3D Environment Exploration Problem Curiosity Driven Exploration

June 14, 2022

Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
Nicolas Castanet, Sylvain Lamprier, Olivier Sigaud
Stein Variational Gradient Descent Variational Objective Exploration Problem Adaptive Exploration Multi Goal Reinforcement Learning

June 1, 2022

Incentivizing Combinatorial Bandit Exploration
Xinyan Hu, Dung Daniel Ngo, Aleksandrs Slivkins, Zhiwei Steven Wu
Bandit Algorithm Exploration Problem Combinatorial Bandit Combinatorial Semi Bandit Incentive Compatible

May 31, 2022

REF: A Rapid Exploration Framework for Deploying Autonomous MAVs in Unknown Environments
Akash Patel, Björn Lindqvist, Christoforos Kanellakis, Ali-akbar Agha-mohammadi, George Nikolakopoulos
Unknown Environment Exploration Problem Rapid Exploration Exploration Algorithm Autonomous Exploration Mission

May 23, 2022

An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environments
Alain Andres, Esther Villar-Rodriguez, Javier Del Ser
Reinforcement Learning Intrinsic Motivation Exploration Problem

Exploration Problem

Papers

Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models

Challenges and Opportunities for Large-Scale Exploration with Air-Ground Teams using Semantics

Ariadne and Theseus: Exploration and Rendezvous with Two Mobile Agents in an Unknown Graph

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent

State Machine of Thoughts: Leveraging Past Reasoning Trajectories for Enhancing Problem Solving

Adaptive trajectory-constrained exploration strategy for deep reinforcement learning

Improving Intrinsic Exploration by Creating Stationary Objectives

First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs

Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition

Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation

Multi-Agent Interplay in a Competitive Survival Environment

Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems

E2R: a Hierarchical-Learning inspired Novelty-Search method to generate diverse repertoires of grasping trajectories

Delayed Geometric Discounts: An Alternative Criterion for Reinforcement Learning

Cell-Free Latent Go-Explore

BYOL-Explore: Exploration by Bootstrapped Prediction

Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning

Incentivizing Combinatorial Bandit Exploration

REF: A Rapid Exploration Framework for Deploying Autonomous MAVs in Unknown Environments

An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environments