Index A | B | C | D | E | G | H | I | K | L | M | N | O | P | R | S | T | U | V | W | X A actions (statrl.settings.bandits.adversarial.lipschitz.agents.ALF.ALFLearner attribute) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) Agent (class in statrl.settings.bandits.adversarial.lipschitz.agent) ALFLearner (class in statrl.settings.bandits.adversarial.lipschitz.agents.ALF) all_selected (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) allmax() (in module statrl.settings.utils) AnytimeToKnownHorizonAgentWrapper (class in statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon) Arm (class in statrl.settings.bandits.stochastic.anytime.envs.distributions) B BABA (class in statrl.settings.bandits.stochastic.batch.agents.BABA) baba_schedule() (in module statrl.settings.bandits.stochastic.batch.envs.parametric) BanditAgent (class in statrl.settings.bandits.stochastic.anytime.agent) (class in statrl.settings.bandits.stochastic.knownhorizon.agent) BanditInteraction (class in statrl.settings.bandits.stochastic.anytime.interaction) (class in statrl.settings.bandits.stochastic.knownhorizon.interaction) BatchBanditAgent (class in statrl.settings.bandits.stochastic.batch.agent) BatchBanditInteraction (class in statrl.settings.bandits.stochastic.batch.interaction) BatchBernoulliBandit (class in statrl.settings.bandits.stochastic.batch.envs.parametric) BatchGaussianBandit (class in statrl.settings.bandits.stochastic.batch.envs.parametric) BatchMAB (class in statrl.settings.bandits.stochastic.batch.environment) batchplay() (statrl.settings.bandits.stochastic.batch.agent.BatchBanditAgent method) (statrl.settings.bandits.stochastic.batch.agents._Oracle.Oracle method) (statrl.settings.bandits.stochastic.batch.agents._Random.Random method) (statrl.settings.bandits.stochastic.batch.agents.BABA.BABA method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCB method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCBnaif method) (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED method) BatchTruncatedGaussianBandit (class in statrl.settings.bandits.stochastic.batch.envs.parametric) batchupdate() (statrl.settings.bandits.stochastic.batch.agent.BatchBanditAgent method) (statrl.settings.bandits.stochastic.batch.agents._Oracle.Oracle method) (statrl.settings.bandits.stochastic.batch.agents._Random.Random method) (statrl.settings.bandits.stochastic.batch.agents.BABA.BABA method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCB method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCBnaif method) (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED method) BCB (class in statrl.settings.bandits.stochastic.batch.agents.BCB) BCBnaif (class in statrl.settings.bandits.stochastic.batch.agents.BCB) Bernoulli() (in module statrl.settings.bandits.stochastic.anytime.envs.distributions) BernoulliBandit() (in module statrl.settings.bandits.stochastic.anytime.envs.parametric) BIMED (class in statrl.settings.bandits.stochastic.batch.agents.BIMED) Binomial() (in module statrl.settings.bandits.stochastic.anytime.envs.distributions) BinomialBandit() (in module statrl.settings.bandits.stochastic.anytime.envs.parametric) build_opti() (in module statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle) C categorical_sample() (in module statrl.settings.utils) change_rendermode() (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP method) clear_auxiliaryfiles() (in module statrl.experiments.utils) close() (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv method) (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP method) computeScoreDiffs() (in module statrl.experiments.analyzeruns) cumRewards (statrl.settings.bandits.stochastic.anytime.agents.IMED.IMED attribute) D Dirac (class in statrl.settings.utils) dirac (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) DiscreteMDP (class in statrl.settings.markovdecisionprocess.discrete_nostructure.environment) dump() (in module statrl.experiments.utils) E epsilon (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) ErgodicRiverSwim (class in statrl.settings.markovdecisionprocess.discrete_nostructure.envs.riverswim) exotic_schedule() (in module statrl.settings.bandits.stochastic.batch.envs.parametric) expected_reward() (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv method) (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP method) Exponential() (in module statrl.settings.bandits.stochastic.anytime.envs.distributions) extractRewardsAndTransitions() (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_controller method) G Gaussian() (in module statrl.settings.bandits.stochastic.anytime.envs.distributions) GaussianBandit() (in module statrl.settings.bandits.stochastic.anytime.envs.parametric) getMeanReward() (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP method) getTransition() (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP method) H horizon (statrl.settings.bandits.stochastic.knownhorizon.agent.BanditAgent attribute) Human (class in statrl.settings.markovdecisionprocess.discrete_nostructure.agents.Human) I IMED (class in statrl.settings.bandits.stochastic.anytime.agents.IMED) IMEDRL (class in statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL) index (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) indexes (statrl.settings.bandits.stochastic.anytime.agents.IMED.IMED attribute) (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED attribute) Interaction (class in statrl.experiments.onerun) K keyboard_waitfor() (in module statrl.settings.markovdecisionprocess.discrete_nostructure.agents.Human) kl (statrl.settings.bandits.stochastic.anytime.agents.IMED.IMED attribute) klBern() (in module statrl.settings.utils) klExp() (in module statrl.settings.utils) klGauss() (in module statrl.settings.utils) KLinf_threshold() (in module statrl.settings.utils) klPoisson() (in module statrl.settings.utils) KnownHorizonToAnytimeAgentWrapper (class in statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon) L last (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP attribute) LipschitzAdversarialEnv (class in statrl.settings.bandits.adversarial.lipschitz.environment) load() (in module statrl.experiments.utils) load_module() (in module statrl.settings.validator) M make() (in module statrl.experiments.utils) max_iteration (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) max_reward (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) maxMeans (statrl.settings.bandits.stochastic.anytime.agents.IMED.IMED attribute) MDPAgent (class in statrl.settings.markovdecisionprocess.discrete_nostructure.agent) MDPInteraction (class in statrl.settings.markovdecisionprocess.discrete_nostructure.interaction) mean (statrl.settings.bandits.stochastic.anytime.envs.distributions.Arm attribute) (statrl.settings.bandits.stochastic.anytime.envs.distributions.TruncatedExponential attribute) mean() (statrl.settings.utils.Dirac method) means (statrl.settings.bandits.stochastic.anytime.agents.IMED.IMED attribute) (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv property) multicoreRuns() (in module statrl.experiments.parallelruns) multinomial_imed() (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL method) N n_actions (statrl.settings.bandits.adversarial.lipschitz.agents.ALF.ALFLearner attribute) nA (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) nameActions (statrl.settings.markovdecisionprocess.discrete_nostructure.envs.riverswim.RiverSwim attribute) nbDraws (statrl.settings.bandits.stochastic.anytime.agents.IMED.IMED attribute) (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED attribute) nbDraws_start (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED attribute) new_episode() (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL method) Nk (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) np_random (statrl.settings.bandits.stochastic.anytime.agent.BanditAgent attribute) (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv attribute) (statrl.settings.bandits.stochastic.batch.agent.BatchBanditAgent attribute) (statrl.settings.bandits.stochastic.knownhorizon.agent.BanditAgent attribute) (statrl.settings.markovdecisionprocess.discrete_nostructure.agent.MDPAgent attribute) nS (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) number_arms (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv property) O oneRunWithDump() (in module statrl.experiments.onerun) Opti_controller (class in statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle) Opti_swimmer (class in statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle) optimal_arm (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv property) optimal_mean (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv property) Oracle (class in statrl.settings.bandits.stochastic.anytime.agents._Oracle) (class in statrl.settings.bandits.stochastic.batch.agents._Oracle) P p_pseudoCounts (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) p_sampled (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) phi (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) play() (statrl.settings.bandits.stochastic.batch.agent.BatchBanditAgent method) (statrl.settings.bandits.stochastic.batch.agents._Oracle.Oracle method) (statrl.settings.bandits.stochastic.batch.agents._Random.Random method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCB method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCBnaif method) (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agent.MDPAgent method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_controller method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_swimmer method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Random.Random method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.Human.Human method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL method) plotlabels (statrl.experiments.onerun.Interaction property) (statrl.settings.bandits.stochastic.anytime.interaction.BanditInteraction property) (statrl.settings.bandits.stochastic.batch.interaction.BatchBanditInteraction property) (statrl.settings.bandits.stochastic.knownhorizon.interaction.BanditInteraction property) (statrl.settings.markovdecisionprocess.discrete_nostructure.interaction.MDPInteraction property) plotScoreDiffs() (in module statrl.experiments.plotruns) policy (statrl.settings.bandits.stochastic.anytime.agents._Oracle.Oracle property) (statrl.settings.bandits.stochastic.batch.agents._Oracle.Oracle property) (statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon.AnytimeToKnownHorizonAgentWrapper property) (statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon.KnownHorizonToAnytimeAgentWrapper property) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_controller attribute) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) PSRL (class in statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL) R r_failureCounts (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) r_sampled (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) r_successCounts (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) randmax() (in module statrl.settings.utils) randmin() (in module statrl.settings.utils) Random (class in statrl.settings.bandits.stochastic.anytime.agents._Random) (class in statrl.settings.bandits.stochastic.batch.agents._Random) (class in statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Random) RandomBernoulliBandit() (in module statrl.settings.bandits.stochastic.anytime.envs.parametric) RandomMDP (class in statrl.settings.markovdecisionprocess.discrete_nostructure.envs.randomMDP) render() (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv method) (statrl.settings.bandits.stochastic.anytime.renderers.textrenderer.Textrenderer method) (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP method) (statrl.settings.markovdecisionprocess.discrete_nostructure.renderers.textRenderer.TextRenderer method) renderers (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv attribute) (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP attribute) renderrun() (statrl.experiments.onerun.Interaction method) (statrl.settings.bandits.stochastic.anytime.interaction.BanditInteraction method) (statrl.settings.bandits.stochastic.batch.interaction.BatchBanditInteraction method) (statrl.settings.bandits.stochastic.knownhorizon.interaction.BanditInteraction method) (statrl.settings.markovdecisionprocess.discrete_nostructure.interaction.MDPInteraction method) report() (in module statrl.settings.validator) reset() (statrl.settings.bandits.adversarial.lipschitz.environment.LipschitzAdversarialEnv method) (statrl.settings.bandits.stochastic.anytime.agent.BanditAgent method) (statrl.settings.bandits.stochastic.anytime.agents._Oracle.Oracle method) (statrl.settings.bandits.stochastic.anytime.agents._Random.Random method) (statrl.settings.bandits.stochastic.anytime.agents.IMED.IMED method) (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv method) (statrl.settings.bandits.stochastic.batch.agent.BatchBanditAgent method) (statrl.settings.bandits.stochastic.batch.agents._Oracle.Oracle method) (statrl.settings.bandits.stochastic.batch.agents._Random.Random method) (statrl.settings.bandits.stochastic.batch.agents.BABA.BABA method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCB method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCBnaif method) (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED method) (statrl.settings.bandits.stochastic.batch.environment.BatchMAB method) (statrl.settings.bandits.stochastic.knownhorizon.agent.BanditAgent method) (statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon.AnytimeToKnownHorizonAgentWrapper method) (statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon.KnownHorizonToAnytimeAgentWrapper method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agent.MDPAgent method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_controller method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_swimmer method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Random.Random method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.Human.Human method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL method) (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP method) reshapeDistribution() (statrl.settings.markovdecisionprocess.discrete_nostructure.envs.randomMDP.RandomMDP method) reward_range (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP attribute) rewardHistory (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED attribute) rewards (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) rewards_distributions (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) RiverSwim (class in statrl.settings.markovdecisionprocess.discrete_nostructure.envs.riverswim) round (statrl.settings.bandits.stochastic.batch.environment.BatchMAB attribute) run() (statrl.experiments.onerun.Interaction method) (statrl.settings.bandits.stochastic.anytime.interaction.BanditInteraction method) (statrl.settings.bandits.stochastic.batch.interaction.BatchBanditInteraction method) (statrl.settings.bandits.stochastic.knownhorizon.interaction.BanditInteraction method) (statrl.settings.markovdecisionprocess.discrete_nostructure.interaction.MDPInteraction method) run_lipschitz_online_learning() (in module statrl.settings.bandits.adversarial.lipschitz.interaction) runLargeMulticoreExperiment() (in module statrl.experiments.massiveruns) rvs() (statrl.settings.utils.Dirac method) S s (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP attribute) sample() (statrl.settings.bandits.stochastic.anytime.envs.distributions.Arm method) (statrl.settings.bandits.stochastic.anytime.envs.distributions.TruncatedExponential method) sample_many() (statrl.settings.bandits.stochastic.anytime.envs.distributions.Arm method) seed() (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP method) select_arm() (statrl.settings.bandits.adversarial.lipschitz.agent.Agent method) (statrl.settings.bandits.adversarial.lipschitz.agents.ALF.ALFLearner method) (statrl.settings.bandits.stochastic.anytime.agent.BanditAgent method) (statrl.settings.bandits.stochastic.anytime.agents._Oracle.Oracle method) (statrl.settings.bandits.stochastic.anytime.agents._Random.Random method) (statrl.settings.bandits.stochastic.anytime.agents.IMED.IMED method) (statrl.settings.bandits.stochastic.knownhorizon.agent.BanditAgent method) (statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon.AnytimeToKnownHorizonAgentWrapper method) (statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon.KnownHorizonToAnytimeAgentWrapper method) skeleton (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) sparserand() (statrl.settings.markovdecisionprocess.discrete_nostructure.envs.randomMDP.RandomMDP method) start() (statrl.settings.bandits.stochastic.anytime.renderers.textrenderer.Textrenderer method) (statrl.settings.markovdecisionprocess.discrete_nostructure.renderers.textRenderer.TextRenderer method) started (statrl.settings.bandits.stochastic.anytime.renderers.textrenderer.Textrenderer attribute) (statrl.settings.markovdecisionprocess.discrete_nostructure.renderers.textRenderer.TextRenderer attribute) state_action_pulls (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) state_visits (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) step() (statrl.settings.bandits.adversarial.lipschitz.environment.LipschitzAdversarialEnv method) (statrl.settings.bandits.stochastic.anytime.environment.StochasticBanditEnv method) (statrl.settings.bandits.stochastic.batch.environment.BatchMAB method) (statrl.settings.markovdecisionprocess.discrete_nostructure.environment.DiscreteMDP method) StochasticBanditEnv (class in statrl.settings.bandits.stochastic.anytime.environment) stop() (statrl.settings.bandits.stochastic.anytime.renderers.textrenderer.Textrenderer method) (statrl.settings.markovdecisionprocess.discrete_nostructure.renderers.textRenderer.TextRenderer method) T t (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) T_target (statrl.settings.bandits.stochastic.batch.agents.BABA.BABA attribute) Textrenderer (class in statrl.settings.bandits.stochastic.anytime.renderers.textrenderer) TextRenderer (class in statrl.settings.markovdecisionprocess.discrete_nostructure.renderers.textRenderer) time (statrl.settings.bandits.adversarial.lipschitz.agents.ALF.ALFLearner attribute) transitions (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL attribute) TruncatedExponential (class in statrl.settings.bandits.stochastic.anytime.envs.distributions) TruncatedGaussian() (in module statrl.settings.bandits.stochastic.anytime.envs.distributions) TruncatedGaussianBandit() (in module statrl.settings.bandits.stochastic.anytime.envs.parametric) U u (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_controller attribute) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) update() (statrl.settings.bandits.adversarial.lipschitz.agent.Agent method) (statrl.settings.bandits.adversarial.lipschitz.agents.ALF.ALFLearner method) (statrl.settings.bandits.stochastic.anytime.agent.BanditAgent method) (statrl.settings.bandits.stochastic.anytime.agents._Oracle.Oracle method) (statrl.settings.bandits.stochastic.anytime.agents._Random.Random method) (statrl.settings.bandits.stochastic.anytime.agents.IMED.IMED method) (statrl.settings.bandits.stochastic.batch.agent.BatchBanditAgent method) (statrl.settings.bandits.stochastic.batch.agents._Oracle.Oracle method) (statrl.settings.bandits.stochastic.batch.agents._Random.Random method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCB method) (statrl.settings.bandits.stochastic.batch.agents.BCB.BCBnaif method) (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED method) (statrl.settings.bandits.stochastic.knownhorizon.agent.BanditAgent method) (statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon.AnytimeToKnownHorizonAgentWrapper method) (statrl.settings.bandits.stochastic.knownhorizon.wrappers.wrapper_anytime_knownhorizon.KnownHorizonToAnytimeAgentWrapper method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agent.MDPAgent method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_controller method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_swimmer method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Random.Random method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.Human.Human method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL method) updateN() (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL method) V validate_agent() (in module statrl.settings.validator) validate_environment() (in module statrl.settings.validator) validate_environment_yaml() (in module statrl.settings.validator) validate_interaction() (in module statrl.settings.validator) validate_setting() (in module statrl.settings.validator) validate_structure() (in module statrl.settings.validator) value_iteration() (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.IMED_RL.IMEDRL method) variance (statrl.settings.bandits.stochastic.anytime.envs.distributions.TruncatedExponential attribute) VI() (statrl.settings.markovdecisionprocess.discrete_nostructure.agents._Oracle.Opti_controller method) (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL method) vk (statrl.settings.markovdecisionprocess.discrete_nostructure.agents.PSRL.PSRL attribute) W weights (statrl.settings.bandits.adversarial.lipschitz.agents.ALF.ALFLearner attribute) X x_threshold (statrl.settings.bandits.stochastic.batch.agents.BIMED.BIMED attribute)