[PDF][PDF] Empirical analysis of off-policy policy evaluation for reinforcement learning
Off-policy policy evaluation (OPE) is the task of predicting the online performance of a policy
using only pre-collected historical data (collected from an existing deployed policy or set of …
using only pre-collected historical data (collected from an existing deployed policy or set of …
Empirical study of off-policy policy evaluation for reinforcement learning
We offer an experimental benchmark and empirical study for off-policy policy evaluation
(OPE) in reinforcement learning, which is a key problem in many safety critical applications …
(OPE) in reinforcement learning, which is a key problem in many safety critical applications …
SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation
H Kiyohara, R Kishimoto, K Kawakami… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper introduces SCOPE-RL, a comprehensive open-source Python software designed
for offline reinforcement learning (offline RL), off-policy evaluation (OPE), and selection …
for offline reinforcement learning (offline RL), off-policy evaluation (OPE), and selection …
Counterfactual-augmented importance sampling for semi-offline policy evaluation
In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative
evaluation using observational data can help practitioners understand the generalization …
evaluation using observational data can help practitioners understand the generalization …
An instrumental variable approach to confounded off-policy evaluation
Off-policy evaluation (OPE) aims to estimate the return of a target policy using some pre-
collected observational data generated by a potentially different behavior policy. In many …
collected observational data generated by a potentially different behavior policy. In many …
Consistent on-line off-policy evaluation
The problem of on-line off-policy evaluation (OPE) has been actively studied in the last
decade due to its importance both as a stand-alone problem and as a module in a policy …
decade due to its importance both as a stand-alone problem and as a module in a policy …
Policy-adaptive estimator selection for off-policy evaluation
Off-policy evaluation (OPE) aims to accurately evaluate the performance of counterfactual
policies using only offline logged data. Although many estimators have been developed …
policies using only offline logged data. Although many estimators have been developed …
Benchmarks for deep off-policy evaluation
Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline
datasets for both evaluating and selecting complex policies for decision making. The ability …
datasets for both evaluating and selecting complex policies for decision making. The ability …
A review of off-policy evaluation in reinforcement learning
Reinforcement learning (RL) is one of the most vibrant research frontiers in machine
learning and has been recently applied to solve a number of challenging problems. In this …
learning and has been recently applied to solve a number of challenging problems. In this …
Reliable off-policy evaluation for reinforcement learning
In a sequential decision-making problem, off-policy evaluation estimates the expected
cumulative reward of a target policy using logged trajectory data generated from a different …
cumulative reward of a target policy using logged trajectory data generated from a different …