An index of algorithms for offline reinforcement learning (offline-rl)
-
Updated
May 23, 2024
#
off-policy-evaluation
Here are 56 public repositories matching this topic...
Open Bandit Pipeline: a python library for bandit algorithms and off-policy evaluation
-
Updated
Jun 3, 2024 - Python
Implementations and examples of common offline policy evaluation methods in Python.
importance-sampling counterfactual-learning off-policy-evaluation doubly-robust offline-policy-evaluation counterfactual-policy-evaluation
-
Updated
Feb 11, 2023 - Python
SCOPE-RL: A python library for offline reinforcement learning, off-policy evaluation, and selection
-
Updated
Mar 18, 2024 - Python
Reinforcement Learning Short Course
reinforcement-learning q-learning ridesharing policy-gradient dynamic-programming deep-q-network markov-decision-processes policy-iteration value-iteration monte-carlo-methods temporal-differencing-learning model-based-rl policy-based-method fitted-q-iteration off-policy-evaluation offline-rl order-dispatch-recommendation llm-reasoning grpo rlvr
-
Updated
Aug 26, 2026 - Jupyter Notebook
Official repository for "Trajectory World Models for Heterogeneous Environments" (ICML 2025), https://arxiv.org/abs/2502.01366
-
Updated
Oct 6, 2025 - Python
(WSDM2022 Best Paper Award Runner-Up) "Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model"
-
Updated
Jul 16, 2023 - Python
(KDD2023) "Off-Policy Evaluation of Ranking Policies under Diverse User Behavior"
-
Updated
Sep 28, 2023 - Python
Representation Learning for OPE
-
Updated
Jul 12, 2022 - Python
[JASA] Off-Policy Interval Estimation withConfounded Markov Decision Process
reinforcement-learning statistical-inference confidence-intervals causal-inference off-policy-evaluation
-
Updated
Sep 13, 2023 - Python
(NeurIPS2023) "Future-Dependent Value-Based Off-Policy Evaluation in POMDPs"
-
Updated
Oct 24, 2023 - Python
Robust Offline Reinforcement Learning with Heavy-Tailed Rewards
-
Updated
Aug 2, 2024 - Python
HOPES: HVAC optimization with Off-Policy Evaluation and Selection
-
Updated
Sep 16, 2026 - Python
Offline reinforcement learning for sepsis treatment policy evaluation using Conservative Q-Learning on a MIMIC-IV v3.1 Sepsis-3 ICU cohort.
machine-learning reinforcement-learning pytorch cql physionet wis sepsis clinical-ai healthcare-ai off-policy-evaluation mimic-iv offline-reinforcement-learning conservative-q-learning fqe
-
Updated
Jun 4, 2026 - Python
Stateful implementations of OPE algorithms, designed for use in the development of offline RL models
-
Updated
Jan 5, 2026 - Python
Official implementation for "On the Reuse Bias in Off-Policy Reinforcement Learning" (IJCAI 2023)
-
Updated
May 25, 2023 - Python
Offline recommender metrics vs true online lift, graded against a known answer (Open Bandit Dataset). Ends in an evaluation gate that refuses to report a number when the diagnostics say it would be meaningless.
machine-learning recommender-systems contextual-bandits off-policy-evaluation counterfactual-evaluation open-bandit-dataset
-
Updated
Sep 12, 2026 - Python
Implementation of "Deeply-Debiased Off-Policy Interval Estimation" (ICML, 2021) in Python
-
Updated
Aug 4, 2021 - Python
System overview for Metis: a clinical decision-support platform recommending Type-2 diabetes treatments via a Neural Thompson Sampling contextual bandit. Spans three repos , a PyTorch model and inference façade, a FastAPI backend over PostgreSQL and Neo4j, and a Next.js client, with a deterministic safety gate and live bandit simulations.
python machine-learning reinforcement-learning neo4j nextjs postgresql pytorch healthcare server-sent-events thompson-sampling diabetes contextual-bandits clinical-decision-support fastapi off-policy-evaluation
-
Updated
Sep 12, 2026
Small OPE product-gate experiment on the Amazon Music ranking benchmark.
-
Updated
Aug 16, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the off-policy-evaluation topic, visit your repo's landing page and select "manage topics."