Measuring and Characterizing Generalization in Deep Reinforcement Learning.
Sam WittyJun Ki LeeEmma ToschAkanksha AtreyMichael L. LittmanDavid D. JensenPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- state space
- function approximation
- reinforcement learning algorithms
- machine learning
- robotic control
- model free
- supervised learning
- multi agent
- database
- temporal difference learning
- databases
- neural network
- case study
- least squares
- learning algorithm
- learning problems
- evaluation function
- social networks
- dynamic programming
- real time
- partially observable
- control policy
- learning process
- stochastic approximation