On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “behavior-agnostic”

Off-Policy Evaluation via the Regularized Lagrangiancs.LG

Unified DICE estimators as regularized Lagrangians for improved off-policy evaluation.

problem Improving off-policy evaluation from behavior-agnostic data.

method Unified derivation of DICE estimators as regularized Lagrangians of a linear program.

result Dual solutions offer greater flexibility and provide superior estimates in practice.

off-policy evaluation behavior-agnostic data regularized Lagrangians stationary distribution correction dual solutions

2020-07-07abs ↗pdf ↗

Reinforcement Learning via Fenchel-Rockafellar Dualitycs.LG

Unified treatment of reinforcement learning via convex duality.

problem Applying Fenchel-Rockafellar duality to reinforcement learning.

method Unified derivation of various RL settings using convex duality.

result Ability to perform policy evaluation and on-policy policy gradient with offline data.

Reinforcement Learning Convex Duality Policy Evaluation Policy Gradient Offline Data

2020-01-07abs ↗pdf ↗

DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Correctionscs.LG

DualDICE estimates discounted distribution ratios for reinforcement learning datasets.

problem Accurate estimation of discounted stationary distribution ratios for reinforcement learning applications.

method Behavior-agnostic algorithm that avoids importance weights and is theoretically guaranteed.

result Significantly improves off-policy policy evaluation accuracy compared to existing techniques.

reinforcement learning discounted distribution ratios behavior-agnostic off-policy evaluation importance weights avoidance

2019-06-10abs ↗pdf ↗

CoinDICE: Off-Policy Confidence Interval Estimationcs.LG

CoinDICE estimates confidence intervals for unknown behavior policies in reinforcement learning.

problem Estimating value of a target policy using only behavior policy data.

method Function space embedding, generalized empirical likelihood method, Lagrangian optimization.

result Valid confidence intervals with tighter and more accurate estimates than existing methods.

reinforcement learning off-policy evaluation confidence intervals generalized empirical likelihood behavior policies

2020-10-22abs ↗pdf ↗

Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Boundscs.LG

This work develops confidence intervals for off-policy evaluation.

problem Estimating expected reward with uncertainty quantification.

method Primal-dual optimization with kernel Bellman loss and martingale concentration inequality.

result Developed practical algorithm for non-asymptotic confidence intervals.

Off-policy evaluation Confidence intervals Reinforcement learning Primal-dual optimization Kernel Bellman loss

2021-03-09abs ↗pdf ↗