Asymptotic analysis of temporal-difference learning algorithms with constant step-sizes
DOI10.1007/s10994-006-5835-zzbMath1470.68185MaRDI QIDQ5898263
Publication date: 22 November 2006
Published in: Machine Learning (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10994-006-5835-z
Markov chains; stochastic approximation; reinforcement learning; temporal-difference learning; neuro-dynamic programming
62M10: Time series, auto-correlation, regression, etc. in statistics (GARCH)
68W40: Analysis of algorithms
68T05: Learning and adaptive systems in artificial intelligence
60K25: Queueing theory (aspects of probability theory)
60J20: Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.)
Cites Work
- Markov chains and stochastic stability
- The convergence of \(TD(\lambda)\) for general \(\lambda\)
- Least squares policy evaluation algorithms with linear function approximation
- On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
- An analysis of temporal-difference learning with function approximation
- OnActor-Critic Algorithms
- On stability of nonlinear AR processes with Markov switching
- On the convergence of temporal-difference learning with linear function approximation
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item