Sequential Task

Sequential task learning focuses on enabling artificial agents to successfully complete multi-step processes, often involving complex interactions with dynamic environments. Current research emphasizes developing robust algorithms and model architectures, such as hierarchical controllers and those incorporating memory and experience replay, to address challenges like catastrophic forgetting and efficient learning across diverse tasks. This area is crucial for advancing artificial intelligence in robotics, natural language processing, and other fields requiring agents to exhibit adaptable, sequential behavior, ultimately leading to more capable and versatile AI systems.

Papers

November 5, 2024

Hierarchical Orchestra of Policies
Thomas P Cannon, Özgür Simsek
Catastrophic Forgetting Part Whole Hierarchy Prior Policy Continual Reinforcement Learning Lifelong Reinforcement Learning Co Orchestration Sequential Task

September 18, 2024

RAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models
Abhinav Jain, Chris Jermaine, Vaibhav Unhelkar
Large Language Model Language Model Robot Learning LLM Based Agent eXperience Report Multiple Critic Sequential Task Page Wise Feedback LLM Assisted Decision Making

August 5, 2024

From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation
Xin Liu, Chao Hao, Zitong Yu, Huanjing Yue, Jingyu Yang
Human Prediction Action Recognition Recognition Rate Action Anticipation Next Activity Prediction Sequential Task

July 9, 2024

Learning a Distributed Hierarchical Locomotion Controller for Embodied Cooperation
Chuye Hong, Kangyao Huang, Huaping Liu
LeArning Abstract Cooperative Behavior Sequential Task Coordinated Control

July 6, 2024

The Solution for the sequential task continual learning track of the 2nd Greater Bay Area International Algorithm Competition
Sishun Pan, Xixian Wu, Tingmin Li, Longfei Huang, Mingxu Feng, Zhonghua Wan, Yang Yang
Continual Learning Solution Path Lifelong Learning Batch Normalization Layer Sequential Task

March 16, 2024

The Fallacy of Minimizing Cumulative Regret in the Sequential Task Setting
Ziping Xu, Kelly W. Zhang, Susan A. Murphy
Reinforcement Learning Robot Learning Regret Minimization Cumulative Regret Regret Rate Order Optimal Regret Sequential Task

February 8, 2024

Pretrained Generative Language Models as General Learning Frameworks for Sequence-Based Tasks
Ben Fauber
Large Language Model Language Model Machine Learning Generative Language Model Sequential Task Pre Trained Generative Language Model

September 8, 2023

Predictive and Robust Robot Assistance for Sequential Manipulation
Theodoros Stouraitis, Michael Gienger
Manipulation Task Robot Assistance Sequential Manipulation Sequential Task Consistency Constraint Robotic Intervention

June 30, 2023

RObotic MAnipulation Network (ROMAN) $\unicode{x2013}$ Hybrid Hierarchical Learning for Solving Complex Sequential Tasks
Eleftherios Triantafyllidis, Fernando Acero, Zhaocheng Liu, Zhibin Li
Imitation Learning Efficient Hybrid Robot Manipulation Hierarchical Learning Long Horizon Manipulation Task Sequential Task

June 7, 2023

STEPS: A Benchmark for Order Reasoning in Sequential Tasks
Weizhi Wang, Hong Wang, Xifeng Yan
New Benchmark Reasoning Capability Commonsense Reasoning Action Sequence Sample STEP High Level Reasoning Sequential Task Task Formulation

June 5, 2023

Learning Embeddings for Sequential Tasks Using Population of Agents
Mridul Mahajan, Georgios Tzannetos, Goran Radanovic, Adish Singla
Reinforcement Learning Agent Smith Na\"ive Population Learned Embeddings Information Theoretic Framework Sequential Task Task Embeddings

March 17, 2023

Comparing NARS and Reinforcement Learning: An Analysis of ONA and $Q$-Learning Algorithms
Ali Beikmohammadi, Sindri Magnússon
Reinforcement Learning General Analysis Reasoning System Q$ Learning Non Axiomatic Reasoning Sequential Task Q$ Learning Algorithm

March 2, 2023

Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study
Mingxu Tao, Yansong Feng, Dongyan Zhao
Pre Trained Language Model Catastrophic Forgetting Ticket BERT Large Pre Trained Language Model Linear Probing Memory Replay Sequential Task

September 25, 2022

Reward Learning using Structural Motifs in Inverse Reinforcement Learning
Raeid Saqur
High Dimensional Reward Function Inverse Reinforcement Learning Reward Learning Sequential Task Novel Technique Sequence Motif

June 24, 2022

Joint Representation Training in Sequential Tasks with Shared Structure
Aldo Pacchiano, Ofir Nachum, Nilseh Tripuraneni, Peter Bartlett
Reinforcement Learning Joint Representation Episodic Markov Decision Process Parallel Algorithm Sequential Task Shared Model