Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning

DOI10.1016/S0921-8890(01)00113-0zbMath1014.68179OpenAlexW2167647761MaRDI QIDQ4538612

Jun Morimoto, Kenji Doya

Publication date: 14 July 2002

Published in: Robotics and Autonomous Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0921-8890(01)00113-0

zbMATH Keywords

Q-learninghierarchical reinforcement learning architecture

Mathematics Subject Classification ID

Artificial intelligence for robotics (68T40)

Related Items

Early motor development from partially ordered neural-body dynamics: experiments with a cortico-spinal-musculo-skeletal model ⋮ Multiple Model-Based Reinforcement Learning ⋮ Reinforcement learning for a biped robot based on a CPG-actor-critic method ⋮ Probabilistic inference for determining options in reinforcement learning ⋮ Hybrid MDP based integrated hierarchical Q-learning ⋮ Model-Based Reinforcement Learning for Partially Observable Games with Sampling-Based State Estimation ⋮ The Neuronal Replicator Hypothesis ⋮ A Spiking Neural Network Model of an Actor-Critic Learning Agent ⋮ From internal models toward metacognitive AI