• Home
  • Search
  • Hierarchical task decomposition through symbiosis in reinforcement learning
  • Cite Icon32
  • https://doi.org/10.1145/2330163.2330178Copy DOI Icon

Hierarchical task decomposition through symbiosis in reinforcement learning

  • Jul 7, 2012
  • John A Doucette +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Adopting a symbiotic model of evolution separates context for deploying an action from the action itself. Such a separation provides a mechanism for task decomposition in temporal sequence learning. Moreover, previously learned policies are taken to be synonymous with meta actions (actions that are themselves policies). Should solutions to the task not be forthcoming in an initial round of evolution, then solutions from the earlier round represent the 'meta' actions for a new round of evolution. This provides the basis for evolving policy trees. A benchmarking study is performed using the Acrobot handstand task. Solutions to date from reinforcement learning have not been able to approach the performance of those established 14 years ago using an A* search and a priori knowledge regarding the Acrobot energy equations. The proposed symbiotic approach is able to match and, for the first time, better these results. Moreover, unlike previous work, solutions are tested under a broad range of Acrobot initial conditions, with hierarchical solutions providing significantly better generalization performance.

Similar Papers
  • Research Article
  • Citations76

Distributed response to network intrusions using multiagent reinforcement learning

  • Feb 21, 2015
  • Engineering Applications of Artificial Intelligence
  • Kleanthis Malialis +1
  • Research Article

WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving

  • Mar 14, 2026
  • Pengxuan Yang +9
  • Research Article
  • Citations10

Temporal Sequence Learning in Healthy Aging and Amnestic Mild Cognitive Impairment

  • Jul 01, 2013
  • Experimental Aging Research
  • Eva Pirogovsky +6
  • Research Article
  • Citations12

Using hierarchical task decomposition as a grammar to map actions in context: Application to forecasting systems in supply chain planning

  • Jan 08, 2011
  • International Journal of Human-Computer Studies
  • Stavros Asimakopoulos +2
  • Book Chapter
  • Citations3

Dual Pilot and Single Pilot Operations – Hierarchical Task Decomposition Analysis of Doing More with Less

  • Jan 01, 2015
  • John Huddlestone +4
  • Research Article
  • Citations22

Continuous Decision-Making in Lane Changing and Overtaking Maneuvers for Unmanned Vehicles: A Risk-Aware Reinforcement Learning Approach With Task Decomposition

  • Apr 01, 2024
  • IEEE Transactions on Intelligent Vehicles
  • Sifan Wu +5
  • Research Article
  • Citations13

Consistent within-group covariance of septal and temporal hippocampal neurogenesis with behavioral phenotypes for exploration and memory retention across wild and laboratory small rodents

  • Jun 12, 2019
  • Behavioural brain research
  • R Maarten Van Dijk +4
  • Conference Article
  • Citations23

Hierarchical generation of dynamic and nondeterministic quests in games

  • Nov 11, 2014
  • Edirlei Soares De Lima +2
  • Conference Article
  • Citations2

Evolution of Hierarchical Controllers for Multirobot Systems

  • Jul 30, 2014
  • Miguel Duarte +2
  • Conference Article
  • Citations11

Towards continual reinforcement learning through evolutionary meta-learning

  • Jul 13, 2019
  • Djordje Grbic +1
  • Conference Article
  • Citations1

The Parallel HTM Spatial Pooler with Actor Model

  • Jun 13, 2020
  • Damir Dobric +3
  • Research Article
  • Citations1

Performance Improvement of Seismic Response Prediction Using the LSTM-PINN Hybrid Method.

  • Jul 24, 2025
  • Biomimetics (Basel, Switzerland)
  • Seunggoo Kim +2
  • Conference Article
  • Citations13

An associative memory system for incremental learning and temporal sequence

  • Jul 01, 2010
  • Furao Shen +3
  • Research Article
  • Citations102

AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning

  • Aug 01, 2023
  • IEEE Transactions on Vehicular Technology
  • Mohammad Parvini +4
  • Research Article
  • Citations107

Evaluating the temporal context of episodic memory: The role of CA3 and CA1

  • Nov 29, 2007
  • Behavioural brain research
  • Michael R Hunsaker
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.