SCOPE-RL Package Reference#

dataset module#

`scope_rl.dataset.base`	Abstract base class for logged dataset.
`scope_rl.dataset.synthetic`	Class to handle synthetic dataset generation.

policy module#

`scope_rl.policy.head`	Wrapper class to convert greedy policy into stochastic.
`scope_rl.policy.orl`	Meta class to handle Offline Learning (ORL).

ope module#

pipeline#

`scope_rl.ope.input`	Meta class to create input for Off-Policy Evaluation (OPE).
`scope_rl.ope.ope`	Meta class to handle standard and cumulative distribution OPE.
`scope_rl.ope.ops`	Meta class to handle Off-Policy Selection (OPS) and evaluation of OPE/OPS.

OPE estimators#

`scope_rl.ope.estimators_base`	Abstract base class for Off-Policy Estimator.
`scope_rl.ope.discrete.basic_estimators`	Off-Policy Estimators for discrete action cases.
`scope_rl.ope.continuous.basic_estimators`	Off-Policy Estimators for continuous action cases (designed for deterministic evaluation policies).
`scope_rl.ope.discrete.marginal_estimators`	State(-Action) Marginal Off-Policy Estimators for discrete action cases.
`scope_rl.ope.continuous.marginal_estimators`	State(-Action) Marginal Off-Policy Estimators for continuous action cases (designed for deterministic evaluation policies).
`scope_rl.ope.discrete.cumulative_distribution_estimators`	Cumulative Distribution Off-Policy Estimators for discrete action cases.
`scope_rl.ope.continuous.cumulative_distribution_estimators`	Cumulative Distribution Off-Policy Estimators for continuous action cases (designed for deterministic evaluation policies).

weight and value learning methods#

`scope_rl.ope.weight_value_learning.base`	Abstract base class for weight and value learning.
`scope_rl.ope.weight_value_learning.function`	Weight and Value Functions.
`scope_rl.ope.weight_value_learning.augmented_lagrangian_learning_discrete`	Augmented Lagrangian method for weight/value function learning (discrete action cases).
`scope_rl.ope.weight_value_learning.augmented_lagrangian_learning_continuous`	Augmented Lagrangian method for weight/value function learning (continuous action cases).
`scope_rl.ope.weight_value_learning.minimax_weight_learning_discrete`	Minimax weight function learning (discrete action cases).
`scope_rl.ope.weight_value_learning.minimax_weight_learning_continuous`	Minimax weight function learning (continuous action cases).
`scope_rl.ope.weight_value_learning.minimax_value_learning_discrete`	Minimax value function learning (discrete action cases).
`scope_rl.ope.weight_value_learning.minimax_value_learning_continuous`	Minimax value function learning (continuous action cases).

others#

scope_rl.ope.online

On-Policy performance comparison.

others#

scope_rl.utils

Useful tools.

<<< Prev Documentation (Back to Top)