TDprop: Does Adaptive Optimization With Jacobi Preconditioning Help Temporal Difference Learning?
Joshua RomoffPeter HendersonDavid KanaaEmmanuel BengioAhmed TouatiPierre-Luc BaconJoelle PineauPublished in: AAMAS (2021)
Keyphrases
- temporal difference learning
- function approximation
- evaluation function
- fixed point
- game playing
- optimization algorithm
- approximate value iteration
- reinforcement learning
- temporal difference
- markov decision process
- reinforcement learning algorithms
- machine learning
- pairwise
- optical flow
- monte carlo
- function approximators