Stateful implementations of OPE algorithms, designed for use in the development of offline RL models
-
Updated
Sep 18, 2024 - Python
Stateful implementations of OPE algorithms, designed for use in the development of offline RL models
Robust Offline Reinforcement Learning with Heavy-Tailed Rewards
HOPES: HVAC optimization with Off-Policy Evaluation and Selection
Open Bandit Pipeline: a python library for bandit algorithms and off-policy evaluation
Reinforcement Learning Short Course
An index of algorithms for offline reinforcement learning (offline-rl)
SCOPE-RL: A python library for offline reinforcement learning, off-policy evaluation, and selection
Implementation of "Off-Policy Interval Estimation with Confounded Markov Decision Process" (JASA, 2022+)
[NeurIPS 2023] Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation. https://arxiv.org/abs/2310.17146
(NeurIPS2023) "Future-Dependent Value-Based Off-Policy Evaluation in POMDPs"
(KDD2023) "Off-Policy Evaluation of Ranking Policies under Diverse User Behavior"
Off-Policy Interval Estimation withConfounded Markov Decision Process
(WSDM2022 Best Paper Award Runner-Up) "Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model"
On the Reuse Bias in Off-Policy Reinforcement Learning (IJCAI 2023)
Implementation of "A Reinforcement Learning Framework for Dynamic Mediation Analysis" (ICML 2023) in Python.
Implementations and examples of common offline policy evaluation methods in Python.
Conformal Off-policy Prediction
Representation Learning for OPE
Implementation of "A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes" (ICML)
Implementation of Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings (NeurIPS, 2021) in Python
Add a description, image, and links to the off-policy-evaluation topic page so that developers can more easily learn about it.
To associate your repository with the off-policy-evaluation topic, visit your repo's landing page and select "manage topics."