Continuous Environment

Continuous environment research focuses on developing algorithms and models enabling agents to navigate and interact within unbounded, realistically complex 3D spaces, often guided by natural language instructions or other high-level goals. Current research emphasizes robust methods for multi-agent pathfinding, collision avoidance, and efficient exploration strategies, often leveraging large language models, graph-based representations, and reinforcement learning techniques like DDPG and model predictive control. This field is crucial for advancing embodied AI, with applications ranging from autonomous robotics and navigation to human-robot interaction and complex industrial control systems.

Papers

March 21, 2023

Assessor-Guided Learning for Continual Environments
Muhammad Anwar Ma'sum, Mahardhika Pratama, Edwin Lughofer, Weiping Ding, Wisnu Jatmiko
Continual LEArning Meta Learning Continuous Environment Task Incremental Learning

February 27, 2023

Estimation of continuous environments by robot swarms: Correlated networks and decision-making
Mohsen Raoufi, Pawel Romanczuk, Heiko Hamann
Estimation Task Decision Making Multi Robot System Swarm Robotics Robot Swarm Continuous Environment Collective Decision Making Decentralized Multi Robot Correlation Network

February 24, 2023

Neural Laplace Control for Continuous-time Delayed Systems
Samuel Holt, Alihan Hüyük, Zhaozhi Qian, Hao Sun, Mihaela van der Schaar
Offline Reinforcement Learning Continuous Time Offline Reinforcement Learning Algorithm Model Based Offline Reinforcement Learning Continuous Environment Neural Laplace

January 11, 2023

Graph based Environment Representation for Vision-and-Language Navigation in Continuous Environments
Ting Wang, Zongkai Wu, Feiyu Yao, Donglin Wang
Graph Drawing Vision and Language Navigation Cross Modal Attention Continuous Environment Environment Representation New Environment

December 21, 2022

Modelling Controllers for Cyber Physical Systems Using Neural Networks
Aravindakumar Vijayasri Mohan Kumar
Neural Network Cyber Physical Control Design Continuous Environment Control System Model Predictive

November 29, 2022

Posterior Sampling for Continuing Environments
Wanqiao Xu, Shi Dong, Benjamin Van Roy
Reinforcement Learning Posterior Inference Posterior Sampling Continuous Environment Bayesian Regret Agent Environment Interaction

November 18, 2022

Building a Subspace of Policies for Scalable Continual Learning
Jean-Baptiste Gaya, Thang Doan, Lucas Caccia, Laure Soulier, Ludovic Denoyer, Roberta Raileanu
Continual Learning Autonomous Agent Prior Policy Deep Subspace Continuous Environment Subspace Prototype Diverse Behavior

October 19, 2022

When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
Annie Xie, Fahim Tajwar, Archit Sharma, Chelsea Finn
Reinforcement Learning HELP Request Continuous Environment Reversible Dynamic Early Intervention Autonomous Reinforcement Learning

September 28, 2022

Disentangling Transfer in Continual Reinforcement Learning
Maciej Wołczyk, Michał Zając, Razvan Pascanu, Łukasz Kuciński, Piotr Miłoś
Continual Learning Continual Learning Benchmark Continuous Environment Continual Reinforcement Learning

July 10, 2022

Challenging Common Assumptions about Catastrophic Forgetting
Timothée Lesort, Oleksiy Ostapenko, Diganta Misra, Md Rifat Arefin, Pau Rodríguez, Laurent Charlin, Irina Rish
Continual LEArning Catastrophic Forgetting Modeling Assumption Continuous Environment Knowledge Accumulation

June 23, 2022

1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)
Dong An, Zun Wang, Yangguang Li, Yi Wang, Yicong Hong, Yan Huang, Liang Wang, Jing Shao
Vision and Language Navigation Place Solution Continuous Environment Long Horizon Navigation CXR Lt Waypoint Prediction

April 20, 2022

Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments
Jacob Krantz, Stefan Lee
Vision and Language Navigation Continuous Environment Sim2Real Transfer High Level Task

March 23, 2022

An Optical Control Environment for Benchmarking Reinforcement Learning Algorithms
Abulikemu Abuduweili, Changliu Liu
Reinforcement Learning Deep Reinforcement Learning Reinforcement Learning Algorithm Policy Reinforcement Learning Reinforcement Learning Benchmark Continuous Environment

March 5, 2022

Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation
Yicong Hong, Zun Wang, Qi Wu, Stephen Gould
LeArning Abstract Vision and Language Navigation Interpretable Direction Discrete Environment Continuous Environment Habitat Simulator

February 22, 2022

Myriad: a real-world testbed to bridge trajectory optimization and deep learning
Nikolaus H. R. Howe, Simon Dufort-Labbé, Nitarshan Rajkumar, Pierre-Luc Bacon
Deep Learning Real World Trajectory Optimization Continuous Environment Environment Dynamic

Continuous Environment

Papers

Assessor-Guided Learning for Continual Environments

Estimation of continuous environments by robot swarms: Correlated networks and decision-making

Neural Laplace Control for Continuous-time Delayed Systems

Graph based Environment Representation for Vision-and-Language Navigation in Continuous Environments

Modelling Controllers for Cyber Physical Systems Using Neural Networks

Posterior Sampling for Continuing Environments

Building a Subspace of Policies for Scalable Continual Learning

When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning

Disentangling Transfer in Continual Reinforcement Learning

Challenging Common Assumptions about Catastrophic Forgetting

1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)

Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments

An Optical Control Environment for Benchmarking Reinforcement Learning Algorithms

Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation

Myriad: a real-world testbed to bridge trajectory optimization and deep learning