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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “Q-filter”

Accelerating Reinforcement Learning with Suboptimal Guidancecs.LG

Guiding reinforcement learning with suboptimal controllers speeds up training.

problem Sparse rewards in reinforcement learning make exploration inefficient.

method Use a suboptimal controller to guide exploration, applying a Q-filter loss conditionally.

result The approach leads to faster policy refinement and better performance.

Reinforcement Learning Sparse Rewards Controller Guidance Suboptimal Q-filter

2019-11-21abs ↗pdf ↗

Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrationscs.LG

SPReD uses uncertainty to decide imitation from demonstrations.

problem Learning from sparse rewards with few demonstrations.

method Ensemble methods to model Q-value distributions, probabilistic and advantage-based uncertainty quantification.

result Significant gains in reinforcement learning across multiple tasks.

reinforcement learning demonstrations uncertainty policy regularisation sparse rewards

2025-09-19abs ↗pdf ↗