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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “BVFT”

Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learningcs.LG

Paper tackles policy selection in offline RL without hyperparameters.

problem Selecting between policies and value functions in offline RL.

method Designs hyperparameter-free algorithms based on BVFT for policy selection.

result Demonstrates effectiveness in discrete-action benchmarks like Atari.

offline reinforcement learning policy selection value-function selection hyperparameter-free BVFT

2021-10-26abs ↗pdf ↗

Batch Value-function Approximation with Only Realizabilitycs.LG

Breaks the hardness conjecture for batch RL with a novel tournament-based approach.

problem Sample-efficient reinforcement learning from exploratory data.

method BVFT algorithm using pairwise comparison and state-action partition.

result Solves the learning problem in a setting previously thought impossible.

reinforcement learning batch learning value-function approximation exploratory data tournament procedure

2020-08-11abs ↗pdf ↗