Average Reward Reinforcement Learning for Semi-Markov Decision Processes
Authors:
- 24 October 2017
- book chapter
- Published by Springer Nature
- p. 768-777
Abstract
No abstract availableKeywords
This publication has 10 references indexed in Scilit:
- A unified approach to time-aggregated Markov decision processesAutomatica, 2016
- Efficient Average Reward Reinforcement Learning Using Constant Shifting ValuesProceedings of the AAAI Conference on Artificial Intelligence, 2016
- Reinforcement learning algorithms for semi-Markov decision processes with average reward2012
- Incremental Value Iteration for Time-Aggregated Markov-Decision ProcessesIEEE Transactions on Automatic Control, 2007
- Reinforcement learning for long-run average costEuropean Journal of Operational Research, 2004
- A time aggregation approach to Markov decision processesAutomatica, 2002
- Learning Algorithms for Markov Decision Processes with Average CostSIAM Journal on Control and Optimization, 2001
- Solving Semi-Markov Decision Problems Using Average Reward Reinforcement LearningManagement Science, 1999
- A New Value Iteration method for the Average Cost Dynamic Programming ProblemSIAM Journal on Control and Optimization, 1998
- A Reinforcement Learning Method for Maximizing Undiscounted Rewards1993