A Sojourn-Based Approach to Semi-Markov Reinforcement Learning.
Giacomo AscioneSalvatore CuomoPublished in: J. Sci. Comput. (2022)
Keyphrases
- semi markov
- reinforcement learning
- conditional random fields
- function approximation
- model free
- markov decision processes
- optimal policy
- machine learning
- information retrieval
- multi agent
- state space
- active learning
- stochastic approximation
- reinforcement learning algorithms
- higher order
- database
- learning process
- decision making
- genetic algorithm
- real world
- data sets
- real time