Observable Environment

Observable environments, characterized by incomplete or uncertain information, are a central challenge in artificial intelligence, particularly for autonomous agents making decisions and navigating complex tasks. Current research focuses on developing robust algorithms and model architectures, such as deep reinforcement learning with recurrent neural networks and belief-space planning, to address partial observability and improve decision-making in these environments. This research is crucial for advancing autonomous systems in various fields, including robotics, agriculture, and autonomous driving, where agents must operate effectively with limited sensory information. The development of more efficient and reliable methods for handling partial observability is key to unlocking the full potential of these technologies.

Papers

May 22, 2023

Bandit Submodular Maximization for Multi-Robot Coordination in Unpredictable and Partially Observable Environments
Zirui Xu, Xiaofeng Lin, Vasileios Tzoumas
Submodular Maximization Partial Observability Predictability Problem Multi Agent Coordination Observable Environment Optimal Action Multi Robot Coordination Submodular Bandit

May 20, 2023

Interactive Model Expansion in an Observable Environment
Pierre Carbonnelle, Joost Vennekens, Bart Bogaerts, Marc Denecker
Scientific Hypothesis Observable Environment Multiple Solution Feasible Solution Model Expansion

April 30, 2023

Model-free Motion Planning of Autonomous Agents for Complex Tasks in Partially Observable Environments
Junchao Li, Mingyu Cai, Zhen Kan, Shaoping Xiao
Motion Planning Autonomous Agent Deep Q Network Model Free Reinforcement Learning Observable Markov Decision Process Complex Task C POMDPs Observable Environment

April 20, 2023

Filter-Aware Model-Predictive Control
Baris Kayalibay, Atanas Mirchev, Ahmed Agha, Patrick van der Smagt, Justin Bayer
Model Predictive Control Observable Environment Efficient Planning Model Predictive

March 14, 2023

Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring
Merlijn Krale, Thiago D. Simão, Nils Jansen
Reinforcement Learning Markov Decision Process Reinforcement Learning Algorithm Observable Environment

March 6, 2023

The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
Raphael Avalos, Florent Delgrange, Ann Nowé, Guillermo A. Pérez, Diederik M. Roijers
Latent Space Markov Decision Process Observable Environment POMDP Policy Wasserstein Dictionary Sub Optimal Policy Belief Update

February 6, 2023

An intelligent tutor for planning in large partially observable environments
Lovis Heindrich, Saksham Consul, Falk Lieder
Task Planning Observable Environment Optimal Planning AI Tutor Observable Non Deterministic Planning Intelligent Tutor

January 24, 2023

Effective Baselines for Multiple Object Rearrangement Planning in Partially Observable Mapped Environments
Engin Tekin, Elaheh Barati, Nitin Kamra, Ruta Desai
Observable Environment Long Horizon Planning Effective Baseline Multi Object Rearrangement Object Rearrangement Planning

November 3, 2022

Sensor Control for Information Gain in Dynamic, Sparse and Partially Observed Environments
J. Brian Burns, Aravind Sundaresan, Pedro Sequeira, Vidyasagar Sadhu
Reinforcement Learning Many Sparse Predictive Coding Information Gain Observable Environment Non Stationary Environment Autonomous Control Informative Reward

September 11, 2022

Pathfinding in Random Partially Observable Environments with Vision-Informed Deep Reinforcement Learning
Anthony Dowling
Deep Reinforcement Learning Deep Q Network Observable Environment

August 6, 2022

Recurrent networks, hidden states and beliefs in partially observable environments
Gaspard Lambrechts, Adrien Bolland, Damien Ernst
Reinforcement Learning Recurrent Neural Network Optimal Policy Recurrent Network Belief State Near Optimal Policy Observable Environment Hidden State

June 22, 2022

POGEMA: Partially Observable Grid Environment for Multiple Agents
Alexey Skrynnik, Anton Andreychuk, Konstantin Yakovlev, Aleksandr I. Panov
Multiple Agent Observable Environment AI Planning Lifelong MAPF

May 7, 2022

Gaussian Process Self-triggered Policy Search in Weakly Observable Environments
Hikaru Sasaki, Terushi Hirabayashi, Kaoru Kawabata, Takamitsu Matsubara
Observable Environment Object Grasping Control Strategy

April 13, 2022

Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning
Ugo Lecerf, Christelle Yemdji-Tchassi, Pietro Michiardi
Autonomous Vehicle Stochastic Way Stochastic Environment Observable Environment Safe Autonomous Driving Robust Agent Contingency Planning

April 9, 2022

Path-Tree Optimization in Discrete Partially Observable Environments using Rapidly-Exploring Belief-Space Graphs
Camille Phiquepal, Andreas Orthey, Nicolas Viennot, Marc Toussaint
Motion Planning Root to Leaf Path Observable Environment Minimal Path Path Planning Problem Belief Space Graph

April 1, 2022

Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes
Samrudhdhi B. Rangrej, Chetan L. Srinidhi, James J. Clark
Supervised ImageNet Strong Consistency Observable Environment Attention Based Transformer Training Objective Hard Attention

March 16, 2022

Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene
Duo Zheng, Fandong Meng, Qingyi Si, Hairun Fan, Zipeng Xu, Jie Zhou, Fangxiang Feng, Xiaojie Wang
Qualitative Difference Observable Environment SpOT Robot Visual Dialog Referential Game Multi Goal Large Scale Multimodal Dataset Visual Dialog Task

December 31, 2021

Formal Verification of Unknown Dynamical Systems via Gaussian Process Regression
John Jackson, Luca Laurenti, Eric Frew, Morteza Lahijanian
Markov Decision Process Dynamical System Gaussian Process Regression Discrete Time Formal Verification Unknown Dynamic Observable Environment

December 7, 2021

Information is Power: Intrinsic Control via Information Capture
Nicholas Rhinehart, Jenny Wang, Glen Berseth, John D. Co-Reyes, Danijar Hafner, Chelsea Finn, Sergey Levine
Real Power State Space Full Information Deep Reinforcement Intrinsic Motivation Observable Environment Information Acquisition Intrinsic Control

Observable Environment

Papers

Bandit Submodular Maximization for Multi-Robot Coordination in Unpredictable and Partially Observable Environments

Interactive Model Expansion in an Observable Environment

Model-free Motion Planning of Autonomous Agents for Complex Tasks in Partially Observable Environments

Filter-Aware Model-Predictive Control

Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring

The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models

An intelligent tutor for planning in large partially observable environments

Effective Baselines for Multiple Object Rearrangement Planning in Partially Observable Mapped Environments

Sensor Control for Information Gain in Dynamic, Sparse and Partially Observed Environments

Pathfinding in Random Partially Observable Environments with Vision-Informed Deep Reinforcement Learning

Recurrent networks, hidden states and beliefs in partially observable environments

POGEMA: Partially Observable Grid Environment for Multiple Agents

Gaussian Process Self-triggered Policy Search in Weakly Observable Environments

Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning

Path-Tree Optimization in Discrete Partially Observable Environments using Rapidly-Exploring Belief-Space Graphs

Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes

Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene

Formal Verification of Unknown Dynamical Systems via Gaussian Process Regression

Information is Power: Intrinsic Control via Information Capture