Mathematical properties of neuronal TD-rules and differential Hebbian learning: a comparison
From MaRDI portal
Publication:937719
DOI10.1007/s00422-007-0209-6zbMath1146.92002OpenAlexW2143873689WikidataQ37057321 ScholiaQ37057321MaRDI QIDQ937719
Christoph Kolodziejski, Florentin Wörgötter, Bernd Porr
Publication date: 15 August 2008
Published in: Biological Cybernetics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s00422-007-0209-6
Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)
Related Items
A differential Hebbian framework for biologically-plausible motor control ⋮ Toward Nonlinear Local Reinforcement Learning Rules Through Neuroevolution ⋮ On the Asymptotic Equivalence Between Differential Hebbian and Temporal Difference Learning
Cites Work
- Unnamed Item
- Unnamed Item
- Computational consequences of temporally asymmetric learning rules. I: Differential Hebbian learning
- \({\mathcal Q}\)-learning
- The convergence of \(TD(\lambda)\) for general \(\lambda\)
- Robust self-localisation and navigation based on hippocampal place cells
- Temporal Difference Model Reproduces Anticipatory Neural Activity
- Derivatives of the Dirac delta function by explicit construction of sequences
- Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity
- An adaptive optimal controller for discrete-time Markov environments
- Isotropic Sequence Order Learning
- ISO Learning Approximates a Solution to the Inverse-Controller Problem in an Unsupervised Behavioral Paradigm
- How the Shape of Pre- and Postsynaptic Signals Can Influence STDP: A Biophysical Model
- Optimal Spike-Timing-Dependent Plasticity for Precise Action Potential Firing in Supervised Learning
- Strongly Improved Stability and Faster Convergence of Temporal Sequence Learning by Using Input Correlations Only
