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.

168,982 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “value-matching”

Policy Distillation and Value Matching in Multiagent Reinforcement Learningcs.LG

New MARL method combines agent knowledge to reduce complexity.

problem Curse of dimensionality in multiagent reinforcement learning.

method Decomposes multiagent problem into multi-task problem, uses distillation and value-matching.

result Outperforms policy distillation alone and improves learning in both discrete and continuous action spaces.

multiagent reinforcement learning curse of dimensionality actor-critic algorithm distillation value-matching

2019-03-15abs ↗pdf ↗

Neural Augmentation of Kalman Filter with Hypernetwork for Channel Trackingeess.SP

HKF uses neural networks to adapt Kalman filters for dynamic channel tracking.

problem Tracking channels with varying dynamics and Doppler values.

method Combines Kalman filters with hypernetworks for dynamic adaptation.

result HKF achieves up to 2dB gain over Kalman filters at high Doppler values.

Kalman Filter Neural Networks Channel Tracking Doppler Hypernetwork

2021-09-26abs ↗pdf ↗

Rare Event Analysis via Stochastic Optimal Controlstat.ML

A new framework uses stochastic optimal control to estimate rare events more accurately.

problem Estimating rare events like chemical reactions in biomolecules is computationally challenging.

method The approach casts committor estimation as a stochastic optimal control problem, developing direct and off-policy Value Matching losses.

result The framework yields more accurate committor estimates, reaction rates, and equilibrium constants.

rare events stochastic optimal control committor function reactive trajectories metastability

2026-04-14abs ↗pdf ↗