Man pages for jdtrat/dynaq
Tools to Simulate DynaQ Reinforcement Learning Algorithms
| basicVisualization | Get Basic Visualizations for Simulations |
| choice | Choose an Action |
| generateData | Generate Task Simulations |
| getFirstTransition | Get Transition from First to Second State |
| getLogFit | Get the Logistic Regression Fit |
| getLogPreds | Get the Logistic Regression Predictions |
| getQGraphicValues | Get Q Values for Plotting |
| getReward | Check for Reward Outcome |
| getSecondTransition | Get Transition from Second to Third State |
| interleave | Interleave two dataframes |
| logSetup | Manipulate the Data for Logistic Regression |
| manipulateData | Manipulate Data |
| oneTrial | Perform One Model-Free Trial |
| processSimData | Process Simulated Data |
| randomChoice | Create a random choice |
| randomPrevious | Get a Random Value from an Existing Dataframe |
| randRewardProb | Random Reward Probability |
| removeTable | Remove Qtable From Data |
| setupQtable | Initialize Q-value Information |
| setupRewards | Setup Rewards |
| setupTransFunction | Setup Transition Model |
| simModel | Perform One Model-Based Trial |
| simTransitionPlot | Plot the Transition Model's Estimates Over Time |
| smaxAction | Action according to Softmax |
| stayDistributionPlot | Plot the Distribution of Stay Probabilities for Multiple... |
| stayProbPlot | Plot the Stay Probability |
| summaryTable | Create a Summary Table of the Stay Probabilities |
| updateQRL | Update QR and QL |
| updateQsecondState | Update Q-values at Second State |
| updateQtable | Update Q Table |
| updateQthirdState | Update Q-values at Third State |
| updateRewardProb | Update Reward Probabilities |
| updateTransFunction | Update Transition Model |
