- sample() (rtbgym.utils.NormalDistribution method), [1]
- sample_action_and_output_pscore() (scope_rl.policy.head.BaseHead method), [1]
- sample_action_and_output_pscore_online() (scope_rl.policy.head.BaseHead method), [1]
- sample_action_online() (scope_rl.policy.head.BaseHead method), [1]
- sample_outcome() (rtbgym.envs.simulator.base.BaseClickAndConversionRate method), [1]
- sample_reward() (basicgym.envs.simulator.base.BaseRewardFunction method), [1]
- save() (scope_rl.ope.weight_value_learning.augmented_lagrangian_learning_continuous.ContinuousDiceStateActionWightValueLearning method), [1]
- (scope_rl.ope.weight_value_learning.augmented_lagrangian_learning_continuous.ContinuousDiceStateWightValueLearning method), [1]
- (scope_rl.ope.weight_value_learning.augmented_lagrangian_learning_discrete.DiscreteDiceStateActionWightValueLearning method), [1]
- (scope_rl.ope.weight_value_learning.augmented_lagrangian_learning_discrete.DiscreteDiceStateWightValueLearning method), [1]
- (scope_rl.ope.weight_value_learning.base.BaseWeightValueLearner method), [1]
- (scope_rl.ope.weight_value_learning.minimax_value_learning_continuous.ContinuousMinimaxStateActionValueLearning method), [1]
- (scope_rl.ope.weight_value_learning.minimax_value_learning_continuous.ContinuousMinimaxStateValueLearning method), [1]
- (scope_rl.ope.weight_value_learning.minimax_value_learning_discrete.DiscreteMinimaxStateActionValueLearning method), [1]
- (scope_rl.ope.weight_value_learning.minimax_value_learning_discrete.DiscreteMinimaxStateValueLearning method), [1]
- (scope_rl.ope.weight_value_learning.minimax_weight_learning_continuous.ContinuousMinimaxStateActionWeightLearning method), [1]
- (scope_rl.ope.weight_value_learning.minimax_weight_learning_continuous.ContinuousMinimaxStateWeightLearning method), [1]
- (scope_rl.ope.weight_value_learning.minimax_weight_learning_discrete.DiscreteMinimaxStateActionWeightLearning method), [1]
- (scope_rl.ope.weight_value_learning.minimax_weight_learning_discrete.DiscreteMinimaxStateWeightLearning method), [1]
-
scope_rl.dataset.base
-
scope_rl.dataset.synthetic
-
scope_rl.ope.continuous.basic_estimators
-
scope_rl.ope.continuous.cumulative_distribution_estimators
-
scope_rl.ope.continuous.marginal_estimators
-
scope_rl.ope.discrete.basic_estimators
-
scope_rl.ope.discrete.cumulative_distribution_estimators
-
scope_rl.ope.discrete.marginal_estimators
-
scope_rl.ope.estimators_base
-
scope_rl.ope.input
-
scope_rl.ope.online
-
scope_rl.ope.ope
-
scope_rl.ope.ops
-
scope_rl.ope.weight_value_learning.augmented_lagrangian_learning_continuous
|
-
scope_rl.ope.weight_value_learning.augmented_lagrangian_learning_discrete
-
scope_rl.ope.weight_value_learning.base
-
scope_rl.ope.weight_value_learning.function
-
scope_rl.ope.weight_value_learning.minimax_value_learning_continuous
-
scope_rl.ope.weight_value_learning.minimax_value_learning_discrete
-
scope_rl.ope.weight_value_learning.minimax_weight_learning_continuous
-
scope_rl.ope.weight_value_learning.minimax_weight_learning_discrete
-
scope_rl.policy.head
-
scope_rl.policy.orl
-
scope_rl.utils
- select_by_conditional_value_at_risk() (scope_rl.ope.ops.OffPolicySelection method), [1]
- select_by_lower_quartile() (scope_rl.ope.ops.OffPolicySelection method), [1]
- select_by_policy_value() (scope_rl.ope.ops.OffPolicySelection method), [1]
- select_by_policy_value_lower_bound() (scope_rl.ope.ops.OffPolicySelection method), [1]
- select_by_policy_value_via_cumulative_distribution_ope() (scope_rl.ope.ops.OffPolicySelection method), [1]
- SelfNormalizedDR (class in scope_rl.ope.continuous.basic_estimators), [1]
- SelfNormalizedPDIS (class in scope_rl.ope.continuous.basic_estimators), [1]
- SelfNormalizedTIS (class in scope_rl.ope.continuous.basic_estimators), [1]
- sigmoid() (in module rtbgym.utils), [1]
- SoftmaxHead (class in scope_rl.policy.head), [1]
- StateActionMarginalDR (class in scope_rl.ope.continuous.marginal_estimators), [1]
- StateActionMarginalIS (class in scope_rl.ope.continuous.marginal_estimators), [1]
- StateActionMarginalSNDR (class in scope_rl.ope.continuous.marginal_estimators), [1]
- StateActionMarginalSNIS (class in scope_rl.ope.continuous.marginal_estimators), [1]
- StateMarginalDM (class in scope_rl.ope.continuous.marginal_estimators), [1]
- StateMarginalDR (class in scope_rl.ope.continuous.marginal_estimators), [1]
- StateMarginalIS (class in scope_rl.ope.continuous.marginal_estimators), [1]
- StateMarginalSNDR (class in scope_rl.ope.continuous.marginal_estimators), [1]
- StateMarginalSNIS (class in scope_rl.ope.continuous.marginal_estimators), [1]
- StateTransitionFunction (class in basicgym.envs.simulator.function), [1]
- StateWeightFunction (class in scope_rl.ope.weight_value_learning.function), [1]
- step() (basicgym.envs.simulator.base.BaseStateTransitionFunction method), [1]
- summarize_off_policy_estimates() (scope_rl.ope.ope.OffPolicyEvaluation method), [1]
- SyntheticDataset (class in scope_rl.dataset.synthetic), [1]
|