Reinforcement Learning with Unbiased Policy Evaluation and Linear Function Approximation.
Anna WinnickiR. SrikantPublished in: CDC (2022)
Keyphrases
- function approximation
- policy evaluation
- reinforcement learning
- temporal difference
- function approximators
- model free
- td learning
- temporal difference learning
- temporal difference methods
- policy iteration
- least squares
- learning tasks
- radial basis function
- reinforcement learning algorithms
- state space
- markov decision processes
- monte carlo
- optimal policy
- neural network
- semi parametric
- dynamic programming
- linear model
- partially observable
- partially observable markov decision processes
- multi agent