Reinforcement learning with replacing eligibility traces

DOI10.1007/BF00114726zbMath0843.68094MaRDI QIDQ1911343

Richard S. Sutton, Satinder Pal Singh

Publication date: 13 August 1996

Published in: Machine Learning (Search for Journal in Brave)

zbMATH Keywords

Monte Carlo methodsreinforcement learningtemporal difference learningeligibility tracereplacing trace

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Guiding exploration by pre-existing knowledge without modifying reward, The optimal unbiased value estimator and its relation to LSTD, TD and MC, Risk-averse policy optimization via risk-neutral policy optimization, A Gentle Introduction to Reinforcement Learning

Cites Work

• Asynchronous stochastic approximation and Q-learning
• Practical issues in temporal difference learning
• The convergence of \(TD(\lambda)\) for general \(\lambda\)
• Temporal-difference methods and Markov models
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• A Note on the Inversion of Matrices by Random Walks
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item