Recent advances in hierarchical reinforcement learning

DOI10.1023/A:1025696116075zbMath1034.93003MaRDI QIDQ5907023

Andrew G. Barto, Sridhar Mahadevan

Publication date: 10 November 2003

Published in: Discrete Event Dynamic Systems (Search for Journal in Brave)

zbMATH Keywords

Markov decision processesoptionreinforcement learninghierarchysemi-Markov decision processestemporal abstractioncurve of dimensionalityMAXQ value function decomposition

Mathematics Subject Classification ID

Hierarchical systems (93A13) Stochastic learning and adaptive control (93E35) Markov and semi-Markov decision processes (90C40)

Related Items (14)

MOSAIC for Multiple-Reward Environments ⋮ AUTOMATIC COMPLEXITY REDUCTION IN REINFORCEMENT LEARNING ⋮ Offline reinforcement learning with task hierarchies ⋮ A penalized h-likelihood variable selection algorithm for generalized linear regression models with random effects ⋮ Improving reinforcement learning by using sequence trees ⋮ Hierarchical Error Representation: A Computational Model of Anterior Cingulate and Dorsolateral Prefrontal Cortex ⋮ Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains ⋮ The explicit form of the rate function for semi-Markov processes and its contractions ⋮ Adapting attackers and defenders patrolling strategies: a reinforcement learning approach for Stackelberg security games ⋮ Model-Based Reinforcement Learning for Partially Observable Games with Sampling-Based State Estimation ⋮ Bottom-up learning of hierarchical models in a class of deterministic pomdp environments ⋮ Induction and Exploitation of Subgoal Automata for Reinforcement Learning ⋮ Continuous-domain ant colony optimization algorithm based on reinforcement learning ⋮ A unified approach to time-aggregated Markov decision processes

This page was built for publication: Recent advances in hierarchical reinforcement learning