Temporal Difference Learning for High-Dimensional PIDEs with Jumps.
Liwei LuHailong GuoXu YangYi ZhuPublished in: SIAM J. Sci. Comput. (2024)
Keyphrases
- temporal difference learning
- high dimensional
- function approximation
- fixed point
- reinforcement learning
- game playing
- evaluation function
- temporal difference
- approximate value iteration
- markov chain
- reinforcement learning algorithms
- markov decision process
- data points
- feature space
- monte carlo
- dynamic environments
- kernel function
- sufficient conditions
- step size
- state space