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

3 results for “FPG”

Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iterationstat.ML

Paper proposes FPG algorithm for unbiased off-policy PG estimation.

problem Challenges in off-policy policy gradient estimation.

method Double Fitted PG estimation (FPG) algorithm for arbitrary policy parameterization.

result Empirically, FPG significantly outperforms existing methods.

policy gradient off-policy double fitted FPG bias reduction

2022-01-31abs ↗pdf ↗

Fractional Policy Gradients: Reinforcement Learning with Long-Term Memorycs.LG

FPG uses fractional calculus for efficient reinforcement learning with long-term memory.

problem High variance and inefficient sampling in standard policy gradient methods for long-term temporal modeling.

method Fractional Policy Gradients (FPG) incorporating Caputo fractional derivatives for power-law temporal correlations.

result Achieves asymptotic variance reduction of order O(t^(-alpha)) and sample efficiency gains.

reinforcement learning fractional calculus long-term memory policy optimization temporal modeling

2025-06-29abs ↗pdf ↗

Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPscs.LG

FPGs use structure to improve policy learning in complex tasks.

problem Policy gradient methods struggle with high-dimensional action spaces and objective multiplicity.

method Factor baseline and action-target influence network to reduce gradient variance.

result FPGs provide a general framework for state-of-the-art algorithms and improve performance.

policy gradients action-target influence MOMDPs variance reduction spatial approximation

2021-02-20abs ↗pdf ↗