Multi-Step Reinforcement Learning: A Unifying Algorithm.
Kristopher De AsisJ. Fernando Hernandez-GarciaG. Zacharias HollandRichard S. SuttonPublished in: AAAI (2018)
Keyphrases
- multi step
- learning algorithm
- reinforcement learning
- objective function
- dynamic programming
- neural network
- data sets
- convergence rate
- convex hull
- dimensionality reduction
- optimization algorithm
- lower bounding
- lower and upper bounds
- markov decision processes
- k means
- pairwise
- lower bound
- optimal solution
- machine learning