Exploration Method

Exploration methods in robotics and reinforcement learning aim to efficiently discover and map unknown environments or optimal policies in complex scenarios, focusing on maximizing information gain while minimizing resource consumption. Current research emphasizes diverse approaches, including bio-inspired multi-agent frameworks, active mapping techniques leveraging semantic information and graph-based representations, and novel exploration strategies within reinforcement learning algorithms like those employing upper confidence bounds or intrinsic rewards based on state entropy or local dependencies. These advancements are crucial for improving the autonomy and efficiency of robots in various applications, from environmental monitoring to complex manipulation tasks, and for accelerating the learning process in reinforcement learning agents.

Papers

February 13, 2023

Guiding Pretraining in Reinforcement Learning with Large Language Models
Yuqing Du, Olivia Watkins, Zihan Wang, Cédric Colas, Trevor Darrell, Pieter Abbeel, Abhishek Gupta, Jacob Andreas
Reinforcement Learning Environment Exploration Exploration Method

February 3, 2023

Multiplier Bootstrap-based Exploration
Runzhe Wan, Haoyu Wei, Branislav Kveton, Rui Song
Exploration Method Instance Dependent Regret Stochastic Multi Armed Bandit Residual Bootstrap

December 27, 2022

Strangeness-driven Exploration in Multi-Agent Reinforcement Learning
Ju-Bong Kim, Ho-Bin Choi, Youn-Hee Han
Multi Agent Reinforcement Learning Efficient Exploration Multi Agent Challenge Exploration Method Curiosity Driven Exploration

November 15, 2022

Learning-Augmented Model-Based Planning for Visual Exploration
Yimeng Li, Arnab Debnath, Gregory Stein, Jana Kosecka
Learning Based Exploration Method Visual Exploration Model Based Planning Based Planner

October 11, 2022

The Role of Exploration for Task Transfer in Reinforcement Learning
Jonathan C Balloch, Julia Kim, and Jessica L Inman, Mark O Riedl
Reinforcement Learning Integral Role Environment Exploration Exploration Method Exploration Exploitation Trade Exploration Strategy

October 6, 2022

Exploration via Planning for Information about the Optimal Trajectory
Viraj Mehta, Ian Char, Joseph Abbate, Rory Conlin, Mark D. Boyer, Stefano Ermon, Jeff Schneider, Willie Neiswanger
Reinforcement Learning Task Planning Environment Exploration Full Information Optimal Trajectory Exploration Method Real World Control Reward Maximizing Policy

September 23, 2022

Multi-Agent Exploration of an Unknown Sparse Landmark Complex via Deep Reinforcement Learning
Xiatao Sun, Yuwei Wu, Subhrajit Bhattacharya, Vijay Kumar
Deep Reinforcement Learning Exploration Method Collaborative Exploration Multi Agent Exploration Agent Exploration Free Exploration

June 25, 2022

Guided Exploration in Reinforcement Learning via Monte Carlo Critic Optimization
Igor Kuznetsov
Reinforcement Learning Exploration Method Guided Exploration Policy Deep Reinforcement Learning Modern Reinforcement Learning Action Correction Unsupervised Calibration

May 2, 2022

Exploration in Deep Reinforcement Learning: A Survey
Pawel Ladosz, Lilian Weng, Minwoo Kim, Hyondong Oh
Reinforcement Learning Timely Survey Deep Reinforcement Learning Environment Exploration Sparse Reward Exploration Method Exploration Strategy

April 22, 2022

Graph Gain: A Concave-Hull Based Volumetric Gain for Robotic Exploration
Zezhou Sun, Huajun Liu, Chengzhong Xu, Hui Kong
Autonomous Exploration Exploration Method Convex Hull Based Exploration Volumetric Effect

March 18, 2022

Online Next-Best-View Planner for 3D-Exploration and Inspection With a Mobile Manipulator Robot
Menaka Naazare, Francisco Garcia Rosas, Dirk Schulz
Autonomous Exploration Mobile Manipulator Visual Inspection Exploration Method Guided Exploration View Planning Exploration Task

March 2, 2022

Follow your Nose: Using General Value Functions for Directed Exploration in Reinforcement Learning
Durgesh Kalwar, Omkar Shelke, Somjit Nath, Hardik Meisheri, Harshad Khadilkar
Reinforcement Learning Value Function Sparse Reward Exploration Method Exploration Strategy Directed Exploration

December 8, 2021

Semantic OcTree Mapping and Shannon Mutual Information Computation for Robot Exploration
Arash Asgharivaskasi, Nikolay Atanasov
Mutual Information Autonomous Exploration Safe Exploration Exploration Method Semantic Octree

November 25, 2021

Interesting Object, Curious Agent: Learning Task-Agnostic Exploration
Simone Parisi, Victoria Dean, Deepak Pathak, Abhinav Gupta
Arbitrary Object Exploration Method Binary Forward Exploration Agnostic Exploration