Man pages for MartinKies/USLR
Reinforcement Learning with R
| Act.A3C | Determines which action the algorithm takes |
| Action.2.Choice.PD | Action to Array for Prisoners Dilemma |
| Action.Encoding.Info.PD | Get Info of Action Encoding |
| Action.Encoding.Info.Simple.Game | Get Info of Action Encoding |
| Act.QLearningPersExpPath | Determines which action to take |
| Advantage.function | Calculates N-Step Returns or weighted Temporal Difference... |
| Alphabet3 | A student strategy |
| a.Mind | A student strategy |
| a.MindHighD | A student strategy |
| a.net.nice0 | A student strategy |
| answer.strat1 | A student strategy |
| answer.strat2 | A student strategy |
| answer.strat3 | A student strategy |
| answer.to.undertaker.2 | A student strategy |
| a.ntft.1 | A student strategy |
| Antimind | A student strategy |
| Antimind2 | A student strategy |
| antiprof2 | A student strategy |
| antistrat2 | A student strategy |
| antistrat2.High.err | A student strategy |
| Antitiktak1 | A student strategy |
| Antitiktak1.improved | An improved Version of AntiTikTak1 |
| Antitiktak1.simplified | A simplified Version of AntiTikTak1 |
| Antitiktak2 | A student strategy |
| a.tadaaa.1 | A student strategy |
| a.td.2 | A student strategy |
| a.TikTak1 | A student strategy |
| a.tiktak.2 | A student strategy |
| Calc.R.phi | deprecated |
| Choice.2.Action.PD | Array to Action for Prisoners Dilemma |
| Choice.2.Action.Simple.Game | Array to Action for Simple Game |
| compare.exploration | Strategy highlighting differences in Exploration states are... |
| Convert.2.train | Converts stored Memory into arrays. |
| counter.da.taaa | A student strategy |
| counter.Mind | A student strategy |
| counter.MindHighD | A student strategy |
| counter.nice.tit.for.tat | A student strategy |
| counter.nice.tit.for.tat.2 | A student strategy |
| counter.rainbow.unicorns.two | A student strategy |
| counter.strat2 | A student strategy |
| counter.ta.daaa | A student strategy |
| counter.tft.forgive.fast | A student strategy |
| counter.tft.forgive.slow | A student strategy |
| counter.the.undertaker.1 | A student strategy |
| counter.the.undertaker.2 | A student strategy |
| da.taaa | A student strategy |
| da.taaa.counter | A student strategy |
| Define_Graph | Graph for Network Loss according to A3C. |
| Define_Graph_Gradient_Update | Graph to update Network weights |
| destab.strat2.0 | A student strategy |
| destab.ta.daaa | A student strategy |
| Discounted.Reward.PD | Update Score based on expected Value of reward |
| dont.forgive | A student strategy |
| dont.mind | A student strategy |
| dont.mind.High.err | A student strategy |
| eat.mindfreaks.2 | A student strategy |
| eat.unicorns.48 | A student strategy |
| eat.unicorns.50 | A student strategy |
| eat.unicorns.65 | A student strategy |
| el.majestro.incredibile | A student strategy |
| Encode.Game.States.PD | Transforms List of Gamestates to std encoding form |
| Encoding.Harper.PD | Encoding based on Reinforcement Learning Produces Dominant... |
| Encoding.last.X.rounds.PD | Flexible Encoding Function which expects the following... |
| Encoding.Manager.PD | Internal Function to make working with different encodings... |
| Extend.Memory.QLearningPersExpPath | Extend Memory by specified experiences |
| External.Eval.PD | Evaluate the current strategy using StratTourn |
| false.friend | A student strategy |
| fix.price.loc | Example srategy for the Hotelling game |
| forgive.slower | A student strategy |
| Generate.Start.State.PD | Generates Start State for Prisoners Dilemma Game |
| Generate.Start.State.Simple.Game | Generates Start State for Simple Game |
| get.against.itself.benchmark | Payoff of strategy against itself |
| get.antistrat | Get vector of names of counter strategy |
| get.benchmark | Payoff of best answer against the strategy |
| get.conversion | Conversion factor |
| Get.Def.Par.A3C | Get Default Parameters of A3C. |
| Get.Def.Par.Neural.Network | Define default Parameters of the Neural Network Function |
| Get.Def.Par.Neural.Network.A3C | Get Default Parameters of the Feed-Forward Neural Network for... |
| Get.Def.Par.Neural.Network.A3C.LSTM | Get Default Parameters of the LSTM Neural Network for the A3C... |
| Get.Def.Par.QLearningPersExpPath | Default Parameters for (improved) Q-Learning |
| Get.Def.Par.QLearningPersExpPath.Legacy.ThesisOpt.XGB | Default Parameters QLearningPersExpPath of the thesis of... |
| Get.Def.Par.QLearningPersExpPath.Legacy.v.0.1.6 | Default Parameters QLearningPersExpPath v.0.1.6 |
| Get.Def.Par.RNN | Define default Parameters of the RNN Function |
| Get.Def.Par.XGBoost | Default Parameters for XGBoost |
| Get.Game.Object.PD | Get Game Object which fully defines Prisoners Dilemma. |
| Get.Game.Object.Simple.Game | Get Game Object which fully defines simple game. |
| Get.Game.Param.PD | Defines the game environment of the IPD |
| Get.Par.PD | Defines model parameters for 'Prisoners Dilemma' |
| Get.Par.Simple.Game | Defines model parameters for 'Simple Game' |
| getrich | A student strategy |
| Globaler.Tit.4.Tat | A student strategy |
| harry | A student strategy |
| Initialise.A3C | Set changeable A3C Parameters. |
| Initialise.QLearningPersExpPath | Set changeable model variables |
| into.spaaaace | A grad student strategy |
| mean.tit.for.tat | A student strategy |
| meineStrat2 | A student strategy |
| Memory.Random.Play.PD | Generate Memory where strategies play against a random... |
| Memory.Self.Play.PD | Generate Memory where strategies play against themselves |
| Mind | A student strategy |
| MindHighD | A student strategy |
| Model.strat.maximum.full.Ten | A strategy to be used after model has been trained |
| nashtag1 | A student strategy |
| net.nice0 | A prof strategy |
| net.nice1 | A variant to net.nice0 |
| net.nice.minus1 | A variant to net.nice0 |
| net.nice.start1 | A variant to net.nice0 |
| nice.tit.for.tat | A student strategy |
| nice.tit.for.tat.High.err | A student strategy |
| NN.strat.full.zero | A strategy to be used after model has been trained |
| NN.strat.main | The actual strategy after model has been trained |
| NN.strat.Slim.TenTen | A strategy to be used after model has been trained |
| NN.strat.Slim.TenTen.QLearning | A strategy to be used after model has been trained |
| NN.strat.static.end.Ten | A strategy to be used after model has been trained |
| nottitfortat | A student strategy |
| overtaker | A student strategy |
| overtaker.High.err | A student strategy |
| phases | A student strategy |
| Play.Multiple.Games.QLearningPersExpPath | Train multiple games |
| Play.On.Strategy.QLearningPersExpPath | Play the game based on strategy |
| Predict.Neural.Network | Evaluate Neural Network |
| Predict.Neural.Network.A3C | Predict Neural Network |
| Predict.RNN | Evaluate Recurrent RNN |
| prep.data.4.shiny | Prepare Worker Memory to visualize with shiny |
| probably.nice.Base | A student strategy |
| probably.nice.High.err | A student strategy |
| probably.not.so.nice | A student strategy |
| probably.not.that.nice | A student strategy |
| prof.strat | A student strategy |
| pudb.strat2 | A student strategy |
| Q.on.hist.PD.QLearning | Q-values based on history of IPD |
| Rainbow.Unicorns.one | A student strategy |
| Rainbow.Unicorns.one.killer | A student strategy |
| Rainbow.Unicorns.two | A student strategy |
| Rainbow.Unicorns.two.killer | A student strategy |
| redim.state | Change dimensionality of the state array. |
| regenbogen | A student strategy |
| Replay.QLearningPersExpPath | Train model of Q learning |
| ron | A student strategy |
| schachmatt_tournament | A student strategy |
| screams.in.space | A grad student strategy |
| seda.strat2 | A student strategy |
| Setup.Neural.Network | Setup a Neural Network |
| Setup.Neural.Network.A3C | Setup a Feed-Forward Neural Network for the... |
| Setup.Neural.Network.A3C.LSTM | Setup a Neural Network with an LSTM-Layer for the... |
| Setup.QLearningPersExpPath | Sets up a model based on model parameters |
| Setup.RNN | Setup a RNN |
| smooth.average | Calculates a sensible moving average based on smoothing... |
| smooth.triangle | Calculates a sensible moving average based on smoothing... |
| squishy.the.octopus | A student strategy |
| State.2.Array.PD | State to Array for Prisoners Dilemma |
| State.2.Array.Simple.Game | State to Array for Simple Game |
| State.Transition.PD | Get next State of Prisoners Dilemma Game |
| State.Transition.Simple.Game | Get next State of Simple Game |
| strat1 | A student strategy |
| strat2 | A student strategy |
| strat2.killer | A student strategy |
| strat3 | A student strategy |
| strat4 | A student strategy |
| stratego | A student strategy |
| strat.fot.tik.tak | A student strategy |
| ta.daaa | A student strategy |
| TakTik1 | A student strategy |
| TakTik2 | A student strategy |
| tatada | A student strategy |
| tft.forgive.fast | A student strategy |
| tft.forgive.fast.2 | A student strategy |
| tft.forgive.fast.killer | A student strategy |
| tft.forgive.slow | A student strategy |
| tft.forgive.slow.killer | A student strategy |
| the.overtaker.1 | A student strategy |
| the.undertaker.1 | A student strategy |
| the.undertaker.2 | A student strategy |
| TikTak1 | A student strategy |
| TikTak2 | A student strategy |
| TokTok | A student strategy |
| Train.A3c | Use the A3C algorithm to train a model |
| Train.Neural.Network | Train Neural Network |
| Train.On.Memory.QLearningPersExpPath | Trains model based on memory |
| Train.QLearningPersExpPath | Train a model based on Q-Learning |
| Train.RNN | Train RNN |
| Update.Evaluator.QLearningPersExpPath | Controlled Copying of Models |
| Update.Memory.QLearningPersExpPath | Add historic Q-Values and Curiosity to memory |
| viva.PD.Strategy | A student strategy |
| Weighted.Discount | Calculates a weighted Mean |
| Worker.A3C | Defines an Agent based on the A3C-Algorithm |
