Exploration with Multiple Random ε-Buffers in Off-Policy Deep Reinforcement Learning.
Chayoung KimJiSu ParkPublished in: Symmetry (2019)
Keyphrases
- reinforcement learning
- artificial intelligence
- reinforcement learning algorithms
- real time
- dynamic programming
- least squares
- data sets
- databases
- machine learning
- information retrieval
- learning algorithm
- markov decision processes
- learning problems
- function approximation
- multiple layers
- model based reinforcement learning