Recent advances in hierarchical reinforcement learning
From MaRDI portal
Publication:5917501
DOI10.1023/A:1022140919877zbMath1018.93035MaRDI QIDQ5917501
Andrew G. Barto, Sridhar Mahadevan
Publication date: 11 May 2003
Published in: Discrete Event Dynamic Systems (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1023/a:1022140919877
reinforcement learning; concurrency; partial observability; hierarchical control; hierarchical memory; temporal abstraction; multiagent coordination; hierarchies of abstract machines; MAXQ framework; options formalism
68Q32: Computational learning theory
93A13: Hierarchical systems
93E35: Stochastic learning and adaptive control
Related Items
Unnamed Item, Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning, Junction Tree Factored Particle Inference Algorithm for Multi-Agent Dynamic Influence Diagrams, A New Policy Evaluation Algorithm for Markov Decision Processes with Quasi Birth-Death Structure, Model-based Reinforcement Learning: A Survey, A synthesis of automated planning and reinforcement learning for efficient, robust decision-making, Hybrid MDP based integrated hierarchical Q-learning, A tutorial on event-based optimization -- a new optimization framework, Distributed reinforcement learning for coordinate multi-robot foraging, Reinforcement learning algorithms with function approximation: recent advances and applications, Reinforcement learning in the brain, Offline reinforcement learning with task hierarchies, Learning and control of exploration primitives, Basic ideas for event-based optimization of Markov systems, Reinforcement learning: an industrial perspective