Topological Visualization Method for Understanding the Landscape of Value Functions and Structure of the State Space in Reinforcement Learning.
Yuki NakamuraTakeshi ShibuyaPublished in: ICAART (2) (2020)
Keyphrases
- reinforcement learning
- state space
- detection method
- basis functions
- significant improvement
- objective function
- dynamic programming
- high accuracy
- data visualization
- high precision
- fourier series
- preprocessing
- pairwise
- markov decision processes
- segmentation method
- policy search
- visualization methods
- function approximation
- tree structure
- optimal policy
- learning algorithm
- feature set
- cost function
- search space