activity
20182021
most citedOff-Policy Evaluation via the Regularized Lagrangian

22 citations · 52 across the 3 of their papers we have counts for

collaborators

7 papers

cs.LG202122 cited

Representation Matters: Offline Pretraining for Sequential Decision Making

Mengjiao Yang, Ofir Nachum

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same para…

cs.CL2021

Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach

Haoming Jiang, Bo Dai, Mengjiao Yang +2

Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turi…

cs.LG20208 cited

Offline Policy Selection under Uncertainty

Mengjiao Yang, Bo Dai, Ofir Nachum +2

The presence of uncertainty in policy evaluation significantly complicates the process of policy ranking and selection in real-world settings. We formally consider offline policy s…

cs.LG202022 cited

Off-Policy Evaluation via the Regularized Lagrangian

Mengjiao Yang, Ofir Nachum, Bo Dai +2

The recently proposed distribution correction estimation (DICE) family of estimators has advanced the state of the art in off-policy evaluation from behavior-agnostic data. While t…

cs.LG2020

Energy-Based Processes for Exchangeable Data

Mengjiao Yang, Bo Dai, Hanjun Dai +1

Recently there has been growing interest in modeling sets with exchangeability such as point clouds. A shortcoming of current approaches is that they restrict the cardinality of th…

cs.LG2019

Benchmarking Attribution Methods with Relative Feature Importance

Mengjiao Yang, Been Kim

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to inpu…