Man pages for XiaoqiLu/PhD-Thesis
Regularized Q-Learning
| BatchGradientQ | Batch Gradient Q-Learning |
| BindSARS | Bind a List of SARS Objects |
| CartPole | CartPole Object |
| CumReward | Cumulative Reward |
| Env | Environment Object |
| EpsilonGreedy | Epsilon-Greedy Action |
| Gaussian | Radial Kernels |
| gibbs | Gibbs Action |
| GradientFQI | Gradient functions for Q-learning |
| greedy | Greedy Action |
| LogSumExp | LogSumExp |
| MSPBE | Objective functions for Q-learning |
| Observe | Observe from Environment |
| Poly | Polynomial Basis |
| ProximalElastic | Proximal Mapping for Elastic Net |
| random | Random Action |
| RBF | Radial Basis Function |
| Reset | Reset the Environment |
| RowWiseKronecker | Row-Wise Kronecker |
| sars | SARS Object |
| SARS2Phis | Convert SARS to Basis Representation |
| Seed | Set Seed for Environment |
| Soft | Soft Thresholding |
| Step | Evolve the Environment |
| Traj | Trajectory Object |
| Traj2SARS | Convert Trajectory to SARS |
